High Resolution Remote Sensing Image Classification Based on Deep Transfer Learning and Multi Feature Network
To improve the automatic classification accuracy of remote sensing images, this study raises a high-resolution remote sensing image classification model that combines deep transfer learning and multi-feature network. In this paper, deep transfer learning is the core technology of remote sensing imag...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10267994/ |
| _version_ | 1797660869647138816 |
|---|---|
| author | Xinyan Huang |
| author_facet | Xinyan Huang |
| author_sort | Xinyan Huang |
| collection | DOAJ |
| description | To improve the automatic classification accuracy of remote sensing images, this study raises a high-resolution remote sensing image classification model that combines deep transfer learning and multi-feature network. In this paper, deep transfer learning is the core technology of remote sensing image classification model, and VGG16, Inception V3, ResNet50 and MobileNet are used to build a fusion classification model through serial fusion. By testing the fusion model, the Transfer Learning ResNet50-MobileNet (TL-RM) model with the best performance was obtained. Finally, experimental analysis verified its significant stability: the average accuracy of TL-RM on a small sample high-resolution remote sensing image dataset was 96.8%, and the Kappa coefficient was 0.964, both of which were the highest values among all models. The accuracy of this model shows a slight upward trend and then stabilizes as the iterations increases. The training and testing sets accuracy ultimately stabilizes at around 100% and 98%, and the loss value ultimately stabilizes at around 1%. Moreover, TL-RM only has a low classification accuracy for residential areas in remote sensing images, with a classification accuracy of over 97% for other categories. The experiment shows that the TL-RM model has significant accuracy and stability, providing a reliable theoretical and experimental basis for remote sensing image classification research. |
| first_indexed | 2024-03-11T18:36:05Z |
| format | Article |
| id | doaj.art-ac5c1b70705e44f4b5030a5eaa790c4f |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T18:36:05Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-ac5c1b70705e44f4b5030a5eaa790c4f2023-10-12T23:00:44ZengIEEEIEEE Access2169-35362023-01-011111007511008510.1109/ACCESS.2023.332079210267994High Resolution Remote Sensing Image Classification Based on Deep Transfer Learning and Multi Feature NetworkXinyan Huang0https://orcid.org/0009-0006-7903-4706School of Computer Science and Technology, Shandong University of Finance and Economics, Jinan, ChinaTo improve the automatic classification accuracy of remote sensing images, this study raises a high-resolution remote sensing image classification model that combines deep transfer learning and multi-feature network. In this paper, deep transfer learning is the core technology of remote sensing image classification model, and VGG16, Inception V3, ResNet50 and MobileNet are used to build a fusion classification model through serial fusion. By testing the fusion model, the Transfer Learning ResNet50-MobileNet (TL-RM) model with the best performance was obtained. Finally, experimental analysis verified its significant stability: the average accuracy of TL-RM on a small sample high-resolution remote sensing image dataset was 96.8%, and the Kappa coefficient was 0.964, both of which were the highest values among all models. The accuracy of this model shows a slight upward trend and then stabilizes as the iterations increases. The training and testing sets accuracy ultimately stabilizes at around 100% and 98%, and the loss value ultimately stabilizes at around 1%. Moreover, TL-RM only has a low classification accuracy for residential areas in remote sensing images, with a classification accuracy of over 97% for other categories. The experiment shows that the TL-RM model has significant accuracy and stability, providing a reliable theoretical and experimental basis for remote sensing image classification research.https://ieeexplore.ieee.org/document/10267994/Transfer learningmultiple featuresCNNremote sensing imagesclassification |
| spellingShingle | Xinyan Huang High Resolution Remote Sensing Image Classification Based on Deep Transfer Learning and Multi Feature Network IEEE Access Transfer learning multiple features CNN remote sensing images classification |
| title | High Resolution Remote Sensing Image Classification Based on Deep Transfer Learning and Multi Feature Network |
| title_full | High Resolution Remote Sensing Image Classification Based on Deep Transfer Learning and Multi Feature Network |
| title_fullStr | High Resolution Remote Sensing Image Classification Based on Deep Transfer Learning and Multi Feature Network |
| title_full_unstemmed | High Resolution Remote Sensing Image Classification Based on Deep Transfer Learning and Multi Feature Network |
| title_short | High Resolution Remote Sensing Image Classification Based on Deep Transfer Learning and Multi Feature Network |
| title_sort | high resolution remote sensing image classification based on deep transfer learning and multi feature network |
| topic | Transfer learning multiple features CNN remote sensing images classification |
| url | https://ieeexplore.ieee.org/document/10267994/ |
| work_keys_str_mv | AT xinyanhuang highresolutionremotesensingimageclassificationbasedondeeptransferlearningandmultifeaturenetwork |