Land-use classification based on high-resolution remote sensing imagery and deep learning models.
High-resolution imagery and deep learning models have gained increasing importance in land-use mapping. In recent years, several new deep learning network modeling methods have surfaced. However, there has been a lack of a clear understanding of the performance of these models. In this study, we app...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2024-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0300473&type=printable |
| _version_ | 1827270004829061120 |
|---|---|
| author | Mengmeng Hao Xiaohan Dong Dong Jiang Xianwen Yu Fangyu Ding Jun Zhuo |
| author_facet | Mengmeng Hao Xiaohan Dong Dong Jiang Xianwen Yu Fangyu Ding Jun Zhuo |
| author_sort | Mengmeng Hao |
| collection | DOAJ |
| description | High-resolution imagery and deep learning models have gained increasing importance in land-use mapping. In recent years, several new deep learning network modeling methods have surfaced. However, there has been a lack of a clear understanding of the performance of these models. In this study, we applied four well-established and robust deep learning models (FCN-8s, SegNet, U-Net, and Swin-UNet) to an open benchmark high-resolution remote sensing dataset to compare their performance in land-use mapping. The results indicate that FCN-8s, SegNet, U-Net, and Swin-UNet achieved overall accuracies of 80.73%, 89.86%, 91.90%, and 96.01%, respectively, on the test set. Furthermore, we assessed the generalization ability of these models using two measures: intersection of union and F1 score, which highlight Swin-UNet's superior robustness compared to the other three models. In summary, our study provides a systematic analysis of the classification differences among these four deep learning models through experiments. It serves as a valuable reference for selecting models in future research, particularly in scenarios such as land-use mapping, urban functional area recognition, and natural resource management. |
| first_indexed | 2024-04-24T06:03:33Z |
| format | Article |
| id | doaj.art-c6e376bfb6d04445b9af0849c25c65e9 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2025-03-22T05:14:32Z |
| publishDate | 2024-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-c6e376bfb6d04445b9af0849c25c65e92024-04-27T05:31:59ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-01194e030047310.1371/journal.pone.0300473Land-use classification based on high-resolution remote sensing imagery and deep learning models.Mengmeng HaoXiaohan DongDong JiangXianwen YuFangyu DingJun ZhuoHigh-resolution imagery and deep learning models have gained increasing importance in land-use mapping. In recent years, several new deep learning network modeling methods have surfaced. However, there has been a lack of a clear understanding of the performance of these models. In this study, we applied four well-established and robust deep learning models (FCN-8s, SegNet, U-Net, and Swin-UNet) to an open benchmark high-resolution remote sensing dataset to compare their performance in land-use mapping. The results indicate that FCN-8s, SegNet, U-Net, and Swin-UNet achieved overall accuracies of 80.73%, 89.86%, 91.90%, and 96.01%, respectively, on the test set. Furthermore, we assessed the generalization ability of these models using two measures: intersection of union and F1 score, which highlight Swin-UNet's superior robustness compared to the other three models. In summary, our study provides a systematic analysis of the classification differences among these four deep learning models through experiments. It serves as a valuable reference for selecting models in future research, particularly in scenarios such as land-use mapping, urban functional area recognition, and natural resource management.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0300473&type=printable |
| spellingShingle | Mengmeng Hao Xiaohan Dong Dong Jiang Xianwen Yu Fangyu Ding Jun Zhuo Land-use classification based on high-resolution remote sensing imagery and deep learning models. PLoS ONE |
| title | Land-use classification based on high-resolution remote sensing imagery and deep learning models. |
| title_full | Land-use classification based on high-resolution remote sensing imagery and deep learning models. |
| title_fullStr | Land-use classification based on high-resolution remote sensing imagery and deep learning models. |
| title_full_unstemmed | Land-use classification based on high-resolution remote sensing imagery and deep learning models. |
| title_short | Land-use classification based on high-resolution remote sensing imagery and deep learning models. |
| title_sort | land use classification based on high resolution remote sensing imagery and deep learning models |
| url | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0300473&type=printable |
| work_keys_str_mv | AT mengmenghao landuseclassificationbasedonhighresolutionremotesensingimageryanddeeplearningmodels AT xiaohandong landuseclassificationbasedonhighresolutionremotesensingimageryanddeeplearningmodels AT dongjiang landuseclassificationbasedonhighresolutionremotesensingimageryanddeeplearningmodels AT xianwenyu landuseclassificationbasedonhighresolutionremotesensingimageryanddeeplearningmodels AT fangyuding landuseclassificationbasedonhighresolutionremotesensingimageryanddeeplearningmodels AT junzhuo landuseclassificationbasedonhighresolutionremotesensingimageryanddeeplearningmodels |