Research on Scene Classification Method of High-Resolution Remote Sensing Images Based on RFPNet
One of the challenges in the field of remote sensing is how to automatically identify and classify high-resolution remote sensing images. A number of approaches have been proposed. Among them, the methods based on low-level visual features and middle-level visual features have limitations. Therefore...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/10/2028 |
| _version_ | 1828919888734846976 |
|---|---|
| author | Xin Zhang Yongcheng Wang Ning Zhang Dongdong Xu Bo Chen |
| author_facet | Xin Zhang Yongcheng Wang Ning Zhang Dongdong Xu Bo Chen |
| author_sort | Xin Zhang |
| collection | DOAJ |
| description | One of the challenges in the field of remote sensing is how to automatically identify and classify high-resolution remote sensing images. A number of approaches have been proposed. Among them, the methods based on low-level visual features and middle-level visual features have limitations. Therefore, this paper adopts the method of deep learning to classify scenes of high-resolution remote sensing images to learn semantic information. Most of the existing methods of convolutional neural networks are based on the existing model using transfer learning, while there are relatively few articles about designing of new convolutional neural networks based on the existing high-resolution remote sensing image datasets. In this context, this paper proposes a multi-view scaling strategy, a new convolutional neural network based on residual blocks and fusing strategy of pooling layer maps, and uses optimization methods to make the convolutional neural network named RFPNet more robust. Experiments on two benchmark remote sensing image datasets have been conducted. On the UC Merced dataset, the test accuracy, precision, recall, and F1-score all exceed 93%. On the SIRI-WHU dataset, the test accuracy, precision, recall, and F1-score all exceed 91%. Compared with the existing methods, such as the most traditional methods and some deep learning methods for scene classification of high-resolution remote sensing images, the proposed method has higher accuracy and robustness. |
| first_indexed | 2024-12-13T21:36:45Z |
| format | Article |
| id | doaj.art-ca30330c1db143d0a26d3ce5df09350f |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-13T21:36:45Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-ca30330c1db143d0a26d3ce5df09350f2022-12-21T23:30:40ZengMDPI AGApplied Sciences2076-34172019-05-01910202810.3390/app9102028app9102028Research on Scene Classification Method of High-Resolution Remote Sensing Images Based on RFPNetXin Zhang0Yongcheng Wang1Ning Zhang2Dongdong Xu3Bo Chen4Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaOne of the challenges in the field of remote sensing is how to automatically identify and classify high-resolution remote sensing images. A number of approaches have been proposed. Among them, the methods based on low-level visual features and middle-level visual features have limitations. Therefore, this paper adopts the method of deep learning to classify scenes of high-resolution remote sensing images to learn semantic information. Most of the existing methods of convolutional neural networks are based on the existing model using transfer learning, while there are relatively few articles about designing of new convolutional neural networks based on the existing high-resolution remote sensing image datasets. In this context, this paper proposes a multi-view scaling strategy, a new convolutional neural network based on residual blocks and fusing strategy of pooling layer maps, and uses optimization methods to make the convolutional neural network named RFPNet more robust. Experiments on two benchmark remote sensing image datasets have been conducted. On the UC Merced dataset, the test accuracy, precision, recall, and F1-score all exceed 93%. On the SIRI-WHU dataset, the test accuracy, precision, recall, and F1-score all exceed 91%. Compared with the existing methods, such as the most traditional methods and some deep learning methods for scene classification of high-resolution remote sensing images, the proposed method has higher accuracy and robustness.https://www.mdpi.com/2076-3417/9/10/2028convolutional neural networkResNetsemantic informationremote sensing imagesscene classificationTensorFlow |
| spellingShingle | Xin Zhang Yongcheng Wang Ning Zhang Dongdong Xu Bo Chen Research on Scene Classification Method of High-Resolution Remote Sensing Images Based on RFPNet Applied Sciences convolutional neural network ResNet semantic information remote sensing images scene classification TensorFlow |
| title | Research on Scene Classification Method of High-Resolution Remote Sensing Images Based on RFPNet |
| title_full | Research on Scene Classification Method of High-Resolution Remote Sensing Images Based on RFPNet |
| title_fullStr | Research on Scene Classification Method of High-Resolution Remote Sensing Images Based on RFPNet |
| title_full_unstemmed | Research on Scene Classification Method of High-Resolution Remote Sensing Images Based on RFPNet |
| title_short | Research on Scene Classification Method of High-Resolution Remote Sensing Images Based on RFPNet |
| title_sort | research on scene classification method of high resolution remote sensing images based on rfpnet |
| topic | convolutional neural network ResNet semantic information remote sensing images scene classification TensorFlow |
| url | https://www.mdpi.com/2076-3417/9/10/2028 |
| work_keys_str_mv | AT xinzhang researchonsceneclassificationmethodofhighresolutionremotesensingimagesbasedonrfpnet AT yongchengwang researchonsceneclassificationmethodofhighresolutionremotesensingimagesbasedonrfpnet AT ningzhang researchonsceneclassificationmethodofhighresolutionremotesensingimagesbasedonrfpnet AT dongdongxu researchonsceneclassificationmethodofhighresolutionremotesensingimagesbasedonrfpnet AT bochen researchonsceneclassificationmethodofhighresolutionremotesensingimagesbasedonrfpnet |