A comparison of unsupervised segmentation parameter optimization approaches using moderate- and high-resolution imagery
Unsupervised segmentation optimization methods have been proposed to aid in selecting an “optimal” set of scale parameters quickly and objectively for object-based image analysis. The goal of this study was to qualitatively assess three unsupervised approaches using both moderate-resolution Landsat...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2017-07-01
|
| Series: | GIScience & Remote Sensing |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/15481603.2017.1287238 |
| _version_ | 1797679114607394816 |
|---|---|
| author | Heather Grybas Lindsay Melendy Russell G. Congalton |
| author_facet | Heather Grybas Lindsay Melendy Russell G. Congalton |
| author_sort | Heather Grybas |
| collection | DOAJ |
| description | Unsupervised segmentation optimization methods have been proposed to aid in selecting an “optimal” set of scale parameters quickly and objectively for object-based image analysis. The goal of this study was to qualitatively assess three unsupervised approaches using both moderate-resolution Landsat and high-resolution Ikonos imagery from two study sites with different landscape characteristics to demonstrate the continued need for analyst intervention during the segmentation process. The results demonstrate that these methods selected parameters that were optimal for the scene which varied with method, image type, and site complexity. Several takeaways from this exercise are as follows: (1) some methods do not work as intended, (2) single-scale unsupervised optimization procedures cannot be expected to properly segment all the features of interest in the image every time, and (3) many multi-scale approaches require subjectively chosen weights or thresholds or additional testing to determine those values that meet the objective. Visual inspection of segmentation results is still required in order to assess over and under-segmentation as no method can be expected to select the best parameters for land cover classifications every time. These approaches should instead be used to narrow down parameter values in order to save time. |
| first_indexed | 2024-03-11T23:09:42Z |
| format | Article |
| id | doaj.art-b227e0e52a6c46deb70f944d1d0e0d64 |
| institution | Directory Open Access Journal |
| issn | 1548-1603 1943-7226 |
| language | English |
| last_indexed | 2024-03-11T23:09:42Z |
| publishDate | 2017-07-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | GIScience & Remote Sensing |
| spelling | doaj.art-b227e0e52a6c46deb70f944d1d0e0d642023-09-21T12:34:13ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262017-07-0154451553310.1080/15481603.2017.12872381287238A comparison of unsupervised segmentation parameter optimization approaches using moderate- and high-resolution imageryHeather Grybas0Lindsay Melendy1Russell G. Congalton2University of New HampshireUniversity of New HampshireUniversity of New HampshireUnsupervised segmentation optimization methods have been proposed to aid in selecting an “optimal” set of scale parameters quickly and objectively for object-based image analysis. The goal of this study was to qualitatively assess three unsupervised approaches using both moderate-resolution Landsat and high-resolution Ikonos imagery from two study sites with different landscape characteristics to demonstrate the continued need for analyst intervention during the segmentation process. The results demonstrate that these methods selected parameters that were optimal for the scene which varied with method, image type, and site complexity. Several takeaways from this exercise are as follows: (1) some methods do not work as intended, (2) single-scale unsupervised optimization procedures cannot be expected to properly segment all the features of interest in the image every time, and (3) many multi-scale approaches require subjectively chosen weights or thresholds or additional testing to determine those values that meet the objective. Visual inspection of segmentation results is still required in order to assess over and under-segmentation as no method can be expected to select the best parameters for land cover classifications every time. These approaches should instead be used to narrow down parameter values in order to save time.http://dx.doi.org/10.1080/15481603.2017.1287238obiaunsupervised segmentationremote sensingsegmentation evaluation |
| spellingShingle | Heather Grybas Lindsay Melendy Russell G. Congalton A comparison of unsupervised segmentation parameter optimization approaches using moderate- and high-resolution imagery GIScience & Remote Sensing obia unsupervised segmentation remote sensing segmentation evaluation |
| title | A comparison of unsupervised segmentation parameter optimization approaches using moderate- and high-resolution imagery |
| title_full | A comparison of unsupervised segmentation parameter optimization approaches using moderate- and high-resolution imagery |
| title_fullStr | A comparison of unsupervised segmentation parameter optimization approaches using moderate- and high-resolution imagery |
| title_full_unstemmed | A comparison of unsupervised segmentation parameter optimization approaches using moderate- and high-resolution imagery |
| title_short | A comparison of unsupervised segmentation parameter optimization approaches using moderate- and high-resolution imagery |
| title_sort | comparison of unsupervised segmentation parameter optimization approaches using moderate and high resolution imagery |
| topic | obia unsupervised segmentation remote sensing segmentation evaluation |
| url | http://dx.doi.org/10.1080/15481603.2017.1287238 |
| work_keys_str_mv | AT heathergrybas acomparisonofunsupervisedsegmentationparameteroptimizationapproachesusingmoderateandhighresolutionimagery AT lindsaymelendy acomparisonofunsupervisedsegmentationparameteroptimizationapproachesusingmoderateandhighresolutionimagery AT russellgcongalton acomparisonofunsupervisedsegmentationparameteroptimizationapproachesusingmoderateandhighresolutionimagery AT heathergrybas comparisonofunsupervisedsegmentationparameteroptimizationapproachesusingmoderateandhighresolutionimagery AT lindsaymelendy comparisonofunsupervisedsegmentationparameteroptimizationapproachesusingmoderateandhighresolutionimagery AT russellgcongalton comparisonofunsupervisedsegmentationparameteroptimizationapproachesusingmoderateandhighresolutionimagery |