An Adversarial Generative Network for Crop Classification from Remote Sensing Timeseries Images
Due to the increasing demand for the monitoring of crop conditions and food production, it is a challenging and meaningful task to identify crops from remote sensing images. The state-of the-art crop classification models are mostly built on supervised classification models such as support vector ma...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/1/65 |
| _version_ | 1797543452723904512 |
|---|---|
| author | Jingtao Li Yonglin Shen Chao Yang |
| author_facet | Jingtao Li Yonglin Shen Chao Yang |
| author_sort | Jingtao Li |
| collection | DOAJ |
| description | Due to the increasing demand for the monitoring of crop conditions and food production, it is a challenging and meaningful task to identify crops from remote sensing images. The state-of the-art crop classification models are mostly built on supervised classification models such as support vector machines (SVM), convolutional neural networks (CNN), and long- and short-term memory neural networks (LSTM). Meanwhile, as an unsupervised generative model, the adversarial generative network (GAN) is rarely used to complete classification tasks for agricultural applications. In this work, we propose a new method that combines GAN, CNN, and LSTM models to classify crops of corn and soybeans from remote sensing time-series images, in which GAN’s discriminator was used as the final classifier. The method is feasible on the condition that the training samples are small, and it fully takes advantage of spectral, spatial, and phenology features of crops from satellite data. The classification experiments were conducted on crops of corn, soybeans, and others. To verify the effectiveness of the proposed method, comparisons with models of SVM, SegNet, CNN, LSTM, and different combinations were also conducted. The results show that our method achieved the best classification results, with the Kappa coefficient of 0.7933 and overall accuracy of 0.86. Experiments in other study areas also demonstrate the extensibility of the proposed method. |
| first_indexed | 2024-03-10T13:44:46Z |
| format | Article |
| id | doaj.art-b002795628574f2eb3c8bf59cfc71a9c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T13:44:46Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b002795628574f2eb3c8bf59cfc71a9c2023-11-21T02:41:24ZengMDPI AGRemote Sensing2072-42922020-12-011316510.3390/rs13010065An Adversarial Generative Network for Crop Classification from Remote Sensing Timeseries ImagesJingtao Li0Yonglin Shen1Chao Yang2School of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaDue to the increasing demand for the monitoring of crop conditions and food production, it is a challenging and meaningful task to identify crops from remote sensing images. The state-of the-art crop classification models are mostly built on supervised classification models such as support vector machines (SVM), convolutional neural networks (CNN), and long- and short-term memory neural networks (LSTM). Meanwhile, as an unsupervised generative model, the adversarial generative network (GAN) is rarely used to complete classification tasks for agricultural applications. In this work, we propose a new method that combines GAN, CNN, and LSTM models to classify crops of corn and soybeans from remote sensing time-series images, in which GAN’s discriminator was used as the final classifier. The method is feasible on the condition that the training samples are small, and it fully takes advantage of spectral, spatial, and phenology features of crops from satellite data. The classification experiments were conducted on crops of corn, soybeans, and others. To verify the effectiveness of the proposed method, comparisons with models of SVM, SegNet, CNN, LSTM, and different combinations were also conducted. The results show that our method achieved the best classification results, with the Kappa coefficient of 0.7933 and overall accuracy of 0.86. Experiments in other study areas also demonstrate the extensibility of the proposed method.https://www.mdpi.com/2072-4292/13/1/65adversarial generative networkcrop classificationdeep learningmultispectral remote sensing |
| spellingShingle | Jingtao Li Yonglin Shen Chao Yang An Adversarial Generative Network for Crop Classification from Remote Sensing Timeseries Images Remote Sensing adversarial generative network crop classification deep learning multispectral remote sensing |
| title | An Adversarial Generative Network for Crop Classification from Remote Sensing Timeseries Images |
| title_full | An Adversarial Generative Network for Crop Classification from Remote Sensing Timeseries Images |
| title_fullStr | An Adversarial Generative Network for Crop Classification from Remote Sensing Timeseries Images |
| title_full_unstemmed | An Adversarial Generative Network for Crop Classification from Remote Sensing Timeseries Images |
| title_short | An Adversarial Generative Network for Crop Classification from Remote Sensing Timeseries Images |
| title_sort | adversarial generative network for crop classification from remote sensing timeseries images |
| topic | adversarial generative network crop classification deep learning multispectral remote sensing |
| url | https://www.mdpi.com/2072-4292/13/1/65 |
| work_keys_str_mv | AT jingtaoli anadversarialgenerativenetworkforcropclassificationfromremotesensingtimeseriesimages AT yonglinshen anadversarialgenerativenetworkforcropclassificationfromremotesensingtimeseriesimages AT chaoyang anadversarialgenerativenetworkforcropclassificationfromremotesensingtimeseriesimages AT jingtaoli adversarialgenerativenetworkforcropclassificationfromremotesensingtimeseriesimages AT yonglinshen adversarialgenerativenetworkforcropclassificationfromremotesensingtimeseriesimages AT chaoyang adversarialgenerativenetworkforcropclassificationfromremotesensingtimeseriesimages |