Crop Classification in a Heterogeneous Arable Landscape Using Uncalibrated UAV Data
Land cover maps are indispensable for decision making, monitoring, and management in agricultural areas, but they are often only available after harvesting. To obtain a timely crop map of a small-scale arable landscape in the Swiss Plateau, we acquired uncalibrated, very high-resolution data, with a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/10/8/1282 |
| _version_ | 1818501813830156288 |
|---|---|
| author | Jonas E. Böhler Michael E. Schaepman Mathias Kneubühler |
| author_facet | Jonas E. Böhler Michael E. Schaepman Mathias Kneubühler |
| author_sort | Jonas E. Böhler |
| collection | DOAJ |
| description | Land cover maps are indispensable for decision making, monitoring, and management in agricultural areas, but they are often only available after harvesting. To obtain a timely crop map of a small-scale arable landscape in the Swiss Plateau, we acquired uncalibrated, very high-resolution data, with a spatial resolution of 0.05 m and four spectral bands, using a consumer-grade camera on an unmanned aerial vehicle (UAV) in June 2015. We resampled the data to different spatial and spectral resolutions, and evaluated the method using textural features (first order statistics and mathematical morphology), a random forest classifier for best performance, as well as number and size of the structuring elements. Our main findings suggest the overall best performing data consisting of a spatial resolution of 0.5 m, three spectral bands (RGB—red, green, and blue), and five different sizes of the structuring elements. The overall accuracy (OA) for the full set of crop classes based on a pixel-based classification is 66.7%. In case of a merged set of crops, the OA increases by ~7% (74.0%). For an object-based classification based on individual field parcels, the OA increases by ~20% (OA of 86.3% for the full set of crop classes, and 94.6% for the merged set, respectively). We conclude the use of UAV to be most relevant at 0.5 m spatial resolution in heterogeneous arable landscapes when used for crop classification. |
| first_indexed | 2024-12-10T21:01:23Z |
| format | Article |
| id | doaj.art-25f77da4fed3447e960a2098b9c75521 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-10T21:01:23Z |
| publishDate | 2018-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-25f77da4fed3447e960a2098b9c755212022-12-22T01:33:47ZengMDPI AGRemote Sensing2072-42922018-08-01108128210.3390/rs10081282rs10081282Crop Classification in a Heterogeneous Arable Landscape Using Uncalibrated UAV DataJonas E. Böhler0Michael E. Schaepman1Mathias Kneubühler2Department of Geography, Remote Sensing Laboratories (RSL), University of Zürich, Winterthurerstrasse 190, 8057 Zürich, SwitzerlandDepartment of Geography, Remote Sensing Laboratories (RSL), University of Zürich, Winterthurerstrasse 190, 8057 Zürich, SwitzerlandDepartment of Geography, Remote Sensing Laboratories (RSL), University of Zürich, Winterthurerstrasse 190, 8057 Zürich, SwitzerlandLand cover maps are indispensable for decision making, monitoring, and management in agricultural areas, but they are often only available after harvesting. To obtain a timely crop map of a small-scale arable landscape in the Swiss Plateau, we acquired uncalibrated, very high-resolution data, with a spatial resolution of 0.05 m and four spectral bands, using a consumer-grade camera on an unmanned aerial vehicle (UAV) in June 2015. We resampled the data to different spatial and spectral resolutions, and evaluated the method using textural features (first order statistics and mathematical morphology), a random forest classifier for best performance, as well as number and size of the structuring elements. Our main findings suggest the overall best performing data consisting of a spatial resolution of 0.5 m, three spectral bands (RGB—red, green, and blue), and five different sizes of the structuring elements. The overall accuracy (OA) for the full set of crop classes based on a pixel-based classification is 66.7%. In case of a merged set of crops, the OA increases by ~7% (74.0%). For an object-based classification based on individual field parcels, the OA increases by ~20% (OA of 86.3% for the full set of crop classes, and 94.6% for the merged set, respectively). We conclude the use of UAV to be most relevant at 0.5 m spatial resolution in heterogeneous arable landscapes when used for crop classification.http://www.mdpi.com/2072-4292/10/8/1282consumer-grade cameraland coververy high resolution (VHR)random forest (RF) classifierobject-based classificationpixel-based classificationsmall-scaled agricultural fieldstexturespatial feature |
| spellingShingle | Jonas E. Böhler Michael E. Schaepman Mathias Kneubühler Crop Classification in a Heterogeneous Arable Landscape Using Uncalibrated UAV Data Remote Sensing consumer-grade camera land cover very high resolution (VHR) random forest (RF) classifier object-based classification pixel-based classification small-scaled agricultural fields texture spatial feature |
| title | Crop Classification in a Heterogeneous Arable Landscape Using Uncalibrated UAV Data |
| title_full | Crop Classification in a Heterogeneous Arable Landscape Using Uncalibrated UAV Data |
| title_fullStr | Crop Classification in a Heterogeneous Arable Landscape Using Uncalibrated UAV Data |
| title_full_unstemmed | Crop Classification in a Heterogeneous Arable Landscape Using Uncalibrated UAV Data |
| title_short | Crop Classification in a Heterogeneous Arable Landscape Using Uncalibrated UAV Data |
| title_sort | crop classification in a heterogeneous arable landscape using uncalibrated uav data |
| topic | consumer-grade camera land cover very high resolution (VHR) random forest (RF) classifier object-based classification pixel-based classification small-scaled agricultural fields texture spatial feature |
| url | http://www.mdpi.com/2072-4292/10/8/1282 |
| work_keys_str_mv | AT jonasebohler cropclassificationinaheterogeneousarablelandscapeusinguncalibrateduavdata AT michaeleschaepman cropclassificationinaheterogeneousarablelandscapeusinguncalibrateduavdata AT mathiaskneubuhler cropclassificationinaheterogeneousarablelandscapeusinguncalibrateduavdata |