Extraction of cropland field parcels with high resolution remote sensing using multi-task learning
ABSTRACTParcel-level farmland information contains rich spatial distribution and boundary details, which is crucial for digital agriculture and agricultural resource surveys. However, the spatial complexity and heterogeneity of features resulting from high resolution makes it difficult to obtain par...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | European Journal of Remote Sensing |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/22797254.2023.2181874 |
| _version_ | 1797869355266998272 |
|---|---|
| author | Leilei Xu Peng Yang Juanjuan Yu Fei Peng Jia Xu Shiran Song Yongxing Wu |
| author_facet | Leilei Xu Peng Yang Juanjuan Yu Fei Peng Jia Xu Shiran Song Yongxing Wu |
| author_sort | Leilei Xu |
| collection | DOAJ |
| description | ABSTRACTParcel-level farmland information contains rich spatial distribution and boundary details, which is crucial for digital agriculture and agricultural resource surveys. However, the spatial complexity and heterogeneity of features resulting from high resolution makes it difficult to obtain parcel-level information quickly and accurately. In addition, existing methods do not sufficiently take into account the spatial topological information, particularly for blurred boundaries. Here, we develop a multi-task network model to extract plot-level cropland information. Specifically, the model consists of a cascaded multi-task network with integrated semantic and edge detection, a refinement network with fixed edge local connectivity, and an integrated fusion model. To validate the performance of the model, two typical tests were conducted in Denmark (Europe) and Chongqing (Asia) with high-resolution remote sensing images provided by Sentinel-2 (10 m) and Google Earth (0.53 m) as data sources. The results show that our proposed model outperforms other baseline models and exhibits higher performance. This study is expected to provide important support for the design of new global agricultural information management systems in the future. |
| first_indexed | 2024-04-10T00:10:13Z |
| format | Article |
| id | doaj.art-a5488a5310cd43a2bde94f5bc42b5e3f |
| institution | Directory Open Access Journal |
| issn | 2279-7254 |
| language | English |
| last_indexed | 2024-04-10T00:10:13Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | European Journal of Remote Sensing |
| spelling | doaj.art-a5488a5310cd43a2bde94f5bc42b5e3f2023-03-16T10:28:30ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542023-12-0156110.1080/22797254.2023.2181874Extraction of cropland field parcels with high resolution remote sensing using multi-task learningLeilei Xu0Peng Yang1Juanjuan Yu2Fei Peng3Jia Xu4Shiran Song5Yongxing Wu6School of Earth Sciences and Engineering, Hohai University, Nanjing, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing, ChinaInstitute of Atmospheric and Environmental Sciences, University of Edinburgh, Edinburgh, UKSchool of Earth Sciences and Engineering, Hohai University, Nanjing, ChinaState Key Laboratory of Desert and Oasis Ecology, Chinese Academy of Sciences, Xinjiang Institute of Ecology and Geography, Urumqi, ChinaUrban Renewal Technology Research Institute, SITRI, Suzhou, chinaABSTRACTParcel-level farmland information contains rich spatial distribution and boundary details, which is crucial for digital agriculture and agricultural resource surveys. However, the spatial complexity and heterogeneity of features resulting from high resolution makes it difficult to obtain parcel-level information quickly and accurately. In addition, existing methods do not sufficiently take into account the spatial topological information, particularly for blurred boundaries. Here, we develop a multi-task network model to extract plot-level cropland information. Specifically, the model consists of a cascaded multi-task network with integrated semantic and edge detection, a refinement network with fixed edge local connectivity, and an integrated fusion model. To validate the performance of the model, two typical tests were conducted in Denmark (Europe) and Chongqing (Asia) with high-resolution remote sensing images provided by Sentinel-2 (10 m) and Google Earth (0.53 m) as data sources. The results show that our proposed model outperforms other baseline models and exhibits higher performance. This study is expected to provide important support for the design of new global agricultural information management systems in the future.https://www.tandfonline.com/doi/10.1080/22797254.2023.2181874High-resolution imagesemantic segmentationedge detection and repaircropland-parcel extractionmulti-task learning |
| spellingShingle | Leilei Xu Peng Yang Juanjuan Yu Fei Peng Jia Xu Shiran Song Yongxing Wu Extraction of cropland field parcels with high resolution remote sensing using multi-task learning European Journal of Remote Sensing High-resolution image semantic segmentation edge detection and repair cropland-parcel extraction multi-task learning |
| title | Extraction of cropland field parcels with high resolution remote sensing using multi-task learning |
| title_full | Extraction of cropland field parcels with high resolution remote sensing using multi-task learning |
| title_fullStr | Extraction of cropland field parcels with high resolution remote sensing using multi-task learning |
| title_full_unstemmed | Extraction of cropland field parcels with high resolution remote sensing using multi-task learning |
| title_short | Extraction of cropland field parcels with high resolution remote sensing using multi-task learning |
| title_sort | extraction of cropland field parcels with high resolution remote sensing using multi task learning |
| topic | High-resolution image semantic segmentation edge detection and repair cropland-parcel extraction multi-task learning |
| url | https://www.tandfonline.com/doi/10.1080/22797254.2023.2181874 |
| work_keys_str_mv | AT leileixu extractionofcroplandfieldparcelswithhighresolutionremotesensingusingmultitasklearning AT pengyang extractionofcroplandfieldparcelswithhighresolutionremotesensingusingmultitasklearning AT juanjuanyu extractionofcroplandfieldparcelswithhighresolutionremotesensingusingmultitasklearning AT feipeng extractionofcroplandfieldparcelswithhighresolutionremotesensingusingmultitasklearning AT jiaxu extractionofcroplandfieldparcelswithhighresolutionremotesensingusingmultitasklearning AT shiransong extractionofcroplandfieldparcelswithhighresolutionremotesensingusingmultitasklearning AT yongxingwu extractionofcroplandfieldparcelswithhighresolutionremotesensingusingmultitasklearning |