Cropland encroachment detection via dual attention and multi-loss based building extraction in remote sensing images
The United Nations predicts that by 2050, the world’s total population will increase to 9.15 billion, but the per capita cropland will drop to 0.151°hm2. The acceleration of urbanization often comes at the expense of the encroachment of cropland, the unplanned expansion of urban area has adversely a...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-09-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2022.993961/full |
| _version_ | 1811260559677456384 |
|---|---|
| author | Junshu Wang Mingrui Cai Yifan Gu Zhen Liu Xiaoxin Li Yuxing Han |
| author_facet | Junshu Wang Mingrui Cai Yifan Gu Zhen Liu Xiaoxin Li Yuxing Han |
| author_sort | Junshu Wang |
| collection | DOAJ |
| description | The United Nations predicts that by 2050, the world’s total population will increase to 9.15 billion, but the per capita cropland will drop to 0.151°hm2. The acceleration of urbanization often comes at the expense of the encroachment of cropland, the unplanned expansion of urban area has adversely affected cultivation. Therefore, the automatic extraction of buildings, which are the main carriers of urban population activities, in remote sensing images has become a more meaningful cropland observation task. To solve the shortcomings of traditional building extraction methods such as insufficient utilization of image information, relying on manual characterization, etc. A U-Net based deep learning building extraction model is proposed and named AttsegGAN. This study proposes an adversarial loss based on the Generative Adversarial Network in terms of training strategy, and the additionally trained learnable discriminator is used as a distance measurer for the two probability distributions of ground truth Pdata and prediction Pg. In addition, for the sharpness of the building edge, the Sobel edge loss based on the Sobel operator is weighted and jointly participated in the training. In WHU building dataset, this study applies the components and strategies step by step, and verifies their effectiveness. Furthermore, the addition of the attention module is also subjected to ablation experiments and the final framework is determined. Compared with the original, AttsegGAN improved by 0.0062, 0.0027, and 0.0055 on Acc, F1, and IoU respectively after adopting all improvements. In the comparative experiment. AttsegGAN is compared with state-of-the-arts including U-Net, DeeplabV3+, PSPNet, and DANet on both WHU and Massachusetts building dataset. In WHU dataset, AttsegGAN achieved 0.9875, 0.9435, and 0.8907 on Acc, F1, and IoU, surpassed U-Net by 0.0260, 0.1183, and 0.1883, respectively, demonstrated the effectiveness of the proposed components in a similar hourglass structure. In Massachusetts dataset, AttsegGAN also surpassed state-of-the-arts, achieved 0.9395, 0.8328, and 0.7130 on Acc, F1, and IoU, respectively, it improved IoU by 0.0412 over the second-ranked PSPNet, and it was 0.0025 and 0.0101 higher than the second place in Acc and F1. |
| first_indexed | 2024-04-12T18:49:24Z |
| format | Article |
| id | doaj.art-a21f75f1ba464520b63cb1cff512db6f |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-04-12T18:49:24Z |
| publishDate | 2022-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-a21f75f1ba464520b63cb1cff512db6f2022-12-22T03:20:31ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2022-09-011310.3389/fpls.2022.993961993961Cropland encroachment detection via dual attention and multi-loss based building extraction in remote sensing imagesJunshu Wang0Mingrui Cai1Yifan Gu2Zhen Liu3Xiaoxin Li4Yuxing Han5College of Electronic Engineering, College of Artificial Intelligence, South China Agricultural University, Guangzhou, ChinaCollege of Electronic Engineering, College of Artificial Intelligence, South China Agricultural University, Guangzhou, ChinaCollege of Electronic Engineering, College of Artificial Intelligence, South China Agricultural University, Guangzhou, ChinaCollege of Electronic Engineering, College of Artificial Intelligence, South China Agricultural University, Guangzhou, ChinaCollege of Electronic Engineering, College of Artificial Intelligence, South China Agricultural University, Guangzhou, ChinaShenzhen International Graduate School, Tsinghua University, Shenzhen, ChinaThe United Nations predicts that by 2050, the world’s total population will increase to 9.15 billion, but the per capita cropland will drop to 0.151°hm2. The acceleration of urbanization often comes at the expense of the encroachment of cropland, the unplanned expansion of urban area has adversely affected cultivation. Therefore, the automatic extraction of buildings, which are the main carriers of urban population activities, in remote sensing images has become a more meaningful cropland observation task. To solve the shortcomings of traditional building extraction methods such as insufficient utilization of image information, relying on manual characterization, etc. A U-Net based deep learning building extraction model is proposed and named AttsegGAN. This study proposes an adversarial loss based on the Generative Adversarial Network in terms of training strategy, and the additionally trained learnable discriminator is used as a distance measurer for the two probability distributions of ground truth Pdata and prediction Pg. In addition, for the sharpness of the building edge, the Sobel edge loss based on the Sobel operator is weighted and jointly participated in the training. In WHU building dataset, this study applies the components and strategies step by step, and verifies their effectiveness. Furthermore, the addition of the attention module is also subjected to ablation experiments and the final framework is determined. Compared with the original, AttsegGAN improved by 0.0062, 0.0027, and 0.0055 on Acc, F1, and IoU respectively after adopting all improvements. In the comparative experiment. AttsegGAN is compared with state-of-the-arts including U-Net, DeeplabV3+, PSPNet, and DANet on both WHU and Massachusetts building dataset. In WHU dataset, AttsegGAN achieved 0.9875, 0.9435, and 0.8907 on Acc, F1, and IoU, surpassed U-Net by 0.0260, 0.1183, and 0.1883, respectively, demonstrated the effectiveness of the proposed components in a similar hourglass structure. In Massachusetts dataset, AttsegGAN also surpassed state-of-the-arts, achieved 0.9395, 0.8328, and 0.7130 on Acc, F1, and IoU, respectively, it improved IoU by 0.0412 over the second-ranked PSPNet, and it was 0.0025 and 0.0101 higher than the second place in Acc and F1.https://www.frontiersin.org/articles/10.3389/fpls.2022.993961/fullUAVcropland observationbuilding extractionWHU building datasetMassachusetts building datasetmulti-loss |
| spellingShingle | Junshu Wang Mingrui Cai Yifan Gu Zhen Liu Xiaoxin Li Yuxing Han Cropland encroachment detection via dual attention and multi-loss based building extraction in remote sensing images Frontiers in Plant Science UAV cropland observation building extraction WHU building dataset Massachusetts building dataset multi-loss |
| title | Cropland encroachment detection via dual attention and multi-loss based building extraction in remote sensing images |
| title_full | Cropland encroachment detection via dual attention and multi-loss based building extraction in remote sensing images |
| title_fullStr | Cropland encroachment detection via dual attention and multi-loss based building extraction in remote sensing images |
| title_full_unstemmed | Cropland encroachment detection via dual attention and multi-loss based building extraction in remote sensing images |
| title_short | Cropland encroachment detection via dual attention and multi-loss based building extraction in remote sensing images |
| title_sort | cropland encroachment detection via dual attention and multi loss based building extraction in remote sensing images |
| topic | UAV cropland observation building extraction WHU building dataset Massachusetts building dataset multi-loss |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2022.993961/full |
| work_keys_str_mv | AT junshuwang croplandencroachmentdetectionviadualattentionandmultilossbasedbuildingextractioninremotesensingimages AT mingruicai croplandencroachmentdetectionviadualattentionandmultilossbasedbuildingextractioninremotesensingimages AT yifangu croplandencroachmentdetectionviadualattentionandmultilossbasedbuildingextractioninremotesensingimages AT zhenliu croplandencroachmentdetectionviadualattentionandmultilossbasedbuildingextractioninremotesensingimages AT xiaoxinli croplandencroachmentdetectionviadualattentionandmultilossbasedbuildingextractioninremotesensingimages AT yuxinghan croplandencroachmentdetectionviadualattentionandmultilossbasedbuildingextractioninremotesensingimages |