Unsupervised Parameterization for Optimal Segmentation of Agricultural Parcels from Satellite Images in Different Agricultural Landscapes
Image segmentation is a cost-effective way to obtain information about the sizes and structural composition of agricultural parcels in an area. To accurately obtain such information, the parameters of the segmentation algorithm ought to be optimized using supervised or unsupervised methods. The diff...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-09-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/18/3096 |
_version_ | 1797553013501460480 |
---|---|
author | Gideon Okpoti Tetteh Alexander Gocht Marcel Schwieder Stefan Erasmi Christopher Conrad |
author_facet | Gideon Okpoti Tetteh Alexander Gocht Marcel Schwieder Stefan Erasmi Christopher Conrad |
author_sort | Gideon Okpoti Tetteh |
collection | DOAJ |
description | Image segmentation is a cost-effective way to obtain information about the sizes and structural composition of agricultural parcels in an area. To accurately obtain such information, the parameters of the segmentation algorithm ought to be optimized using supervised or unsupervised methods. The difficulty in obtaining reference data makes unsupervised methods indispensable. In this study, we evaluated an existing unsupervised evaluation metric that minimizes a global score (<i>GS</i>), which is computed by summing up the intra-segment uniformity and inter-segment dissimilarity within a segmentation output. We modified this metric and proposed a new metric that uses absolute difference to compute the <i>GS</i>. We compared this proposed metric with the existing metric in two optimization approaches based on the Multiresolution Segmentation (MRS) algorithm to optimally delineate agricultural parcels from Sentinel-2 images in Lower Saxony, Germany. The first approach searches for optimal scale while keeping shape and compactness constant, while the second approach uses Bayesian optimization to optimize the three main parameters of the MRS algorithm. Based on a reference data of agricultural parcels, the optimal segmentation result of each optimization approach was evaluated by calculating the quality rate, over-segmentation, and under-segmentation. For both approaches, our proposed metric outperformed the existing metric in different agricultural landscapes. The proposed metric identified optimal segmentations that were less under-segmented compared to the existing metric. A comparison of the optimal segmentation results obtained in this study to existing benchmark results generated via supervised optimization showed that the unsupervised Bayesian optimization approach based on our proposed metric can potentially be used as an alternative to supervised optimization, particularly in geographic regions where reference data is unavailable or an automated evaluation system is sought. |
first_indexed | 2024-03-10T16:09:21Z |
format | Article |
id | doaj.art-16a85ae9011a4aa29fbdeda140c168ed |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T16:09:21Z |
publishDate | 2020-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-16a85ae9011a4aa29fbdeda140c168ed2023-11-20T14:34:01ZengMDPI AGRemote Sensing2072-42922020-09-011218309610.3390/rs12183096Unsupervised Parameterization for Optimal Segmentation of Agricultural Parcels from Satellite Images in Different Agricultural LandscapesGideon Okpoti Tetteh0Alexander Gocht1Marcel Schwieder2Stefan Erasmi3Christopher Conrad4Thünen Institute of Farm Economics, Bundesallee 63, 38116 Braunschweig, GermanyThünen Institute of Farm Economics, Bundesallee 63, 38116 Braunschweig, GermanyThünen Institute of Farm Economics, Bundesallee 63, 38116 Braunschweig, GermanyThünen Institute of Farm Economics, Bundesallee 63, 38116 Braunschweig, GermanyInstitute of Geosciences and Geography, Martin-Luther-University Halle-Wittenberg, 06099 Halle, GermanyImage segmentation is a cost-effective way to obtain information about the sizes and structural composition of agricultural parcels in an area. To accurately obtain such information, the parameters of the segmentation algorithm ought to be optimized using supervised or unsupervised methods. The difficulty in obtaining reference data makes unsupervised methods indispensable. In this study, we evaluated an existing unsupervised evaluation metric that minimizes a global score (<i>GS</i>), which is computed by summing up the intra-segment uniformity and inter-segment dissimilarity within a segmentation output. We modified this metric and proposed a new metric that uses absolute difference to compute the <i>GS</i>. We compared this proposed metric with the existing metric in two optimization approaches based on the Multiresolution Segmentation (MRS) algorithm to optimally delineate agricultural parcels from Sentinel-2 images in Lower Saxony, Germany. The first approach searches for optimal scale while keeping shape and compactness constant, while the second approach uses Bayesian optimization to optimize the three main parameters of the MRS algorithm. Based on a reference data of agricultural parcels, the optimal segmentation result of each optimization approach was evaluated by calculating the quality rate, over-segmentation, and under-segmentation. For both approaches, our proposed metric outperformed the existing metric in different agricultural landscapes. The proposed metric identified optimal segmentations that were less under-segmented compared to the existing metric. A comparison of the optimal segmentation results obtained in this study to existing benchmark results generated via supervised optimization showed that the unsupervised Bayesian optimization approach based on our proposed metric can potentially be used as an alternative to supervised optimization, particularly in geographic regions where reference data is unavailable or an automated evaluation system is sought.https://www.mdpi.com/2072-4292/12/18/3096agricultural parcelsOBIAmultiresolution segmentationunsupervised segmentation evaluationspatial autocorrelationweighted variance |
spellingShingle | Gideon Okpoti Tetteh Alexander Gocht Marcel Schwieder Stefan Erasmi Christopher Conrad Unsupervised Parameterization for Optimal Segmentation of Agricultural Parcels from Satellite Images in Different Agricultural Landscapes Remote Sensing agricultural parcels OBIA multiresolution segmentation unsupervised segmentation evaluation spatial autocorrelation weighted variance |
title | Unsupervised Parameterization for Optimal Segmentation of Agricultural Parcels from Satellite Images in Different Agricultural Landscapes |
title_full | Unsupervised Parameterization for Optimal Segmentation of Agricultural Parcels from Satellite Images in Different Agricultural Landscapes |
title_fullStr | Unsupervised Parameterization for Optimal Segmentation of Agricultural Parcels from Satellite Images in Different Agricultural Landscapes |
title_full_unstemmed | Unsupervised Parameterization for Optimal Segmentation of Agricultural Parcels from Satellite Images in Different Agricultural Landscapes |
title_short | Unsupervised Parameterization for Optimal Segmentation of Agricultural Parcels from Satellite Images in Different Agricultural Landscapes |
title_sort | unsupervised parameterization for optimal segmentation of agricultural parcels from satellite images in different agricultural landscapes |
topic | agricultural parcels OBIA multiresolution segmentation unsupervised segmentation evaluation spatial autocorrelation weighted variance |
url | https://www.mdpi.com/2072-4292/12/18/3096 |
work_keys_str_mv | AT gideonokpotitetteh unsupervisedparameterizationforoptimalsegmentationofagriculturalparcelsfromsatelliteimagesindifferentagriculturallandscapes AT alexandergocht unsupervisedparameterizationforoptimalsegmentationofagriculturalparcelsfromsatelliteimagesindifferentagriculturallandscapes AT marcelschwieder unsupervisedparameterizationforoptimalsegmentationofagriculturalparcelsfromsatelliteimagesindifferentagriculturallandscapes AT stefanerasmi unsupervisedparameterizationforoptimalsegmentationofagriculturalparcelsfromsatelliteimagesindifferentagriculturallandscapes AT christopherconrad unsupervisedparameterizationforoptimalsegmentationofagriculturalparcelsfromsatelliteimagesindifferentagriculturallandscapes |