Three-Channel Convolutional Neural Network for Polarimetric SAR Images Classification
Terrain classification is an important topic in polarimetric synthetic aperture radar (PolSAR) image processing and interpretation. A novel PolSAR classification method based on the three-channel convolutional neural network (Tc-CNN) is proposed and this method can effectively take the advantage of...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9172110/ |
| _version_ | 1824020906575396864 |
|---|---|
| author | Wenqiang Hua Wen Xie Xiaomin Jin |
| author_facet | Wenqiang Hua Wen Xie Xiaomin Jin |
| author_sort | Wenqiang Hua |
| collection | DOAJ |
| description | Terrain classification is an important topic in polarimetric synthetic aperture radar (PolSAR) image processing and interpretation. A novel PolSAR classification method based on the three-channel convolutional neural network (Tc-CNN) is proposed and this method can effectively take the advantage of unlabeled samples to improve the performance of classification with a small number of labeled samples. Several strategies are included in the proposed method. First, in order to take the advantage of unlabeled samples, a data enhancement method based on the neighborhood nearest neighbor propagation method is proposed to enlarge the number of labeled samples. Second, to increase the role of central pixel in convolutional neural network classification based on the pixel, a spatial weighted method is proposed to increase the weight of central pixel features and weak the weight of other types of pixel features. Third, a specific deep model for PolSAR image classification (named Tc-CNN) is proposed, which can obtain more scale and deep polarization information to improve the classification results. The experimental results show that the proposed method achieves a much better performance than the existing classification methods when the number of labeled samples is few. |
| first_indexed | 2024-12-19T01:37:30Z |
| format | Article |
| id | doaj.art-1737eb7e696a44ef9f798c4f0698d13e |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-19T01:37:30Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-1737eb7e696a44ef9f798c4f0698d13e2022-12-21T20:41:53ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352020-01-01134895490710.1109/JSTARS.2020.30181619172110Three-Channel Convolutional Neural Network for Polarimetric SAR Images ClassificationWenqiang Hua0https://orcid.org/0000-0003-2611-6194Wen Xie1Xiaomin Jin2https://orcid.org/0000-0003-4622-8361Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an, ChinaShaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an, ChinaShaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an, ChinaTerrain classification is an important topic in polarimetric synthetic aperture radar (PolSAR) image processing and interpretation. A novel PolSAR classification method based on the three-channel convolutional neural network (Tc-CNN) is proposed and this method can effectively take the advantage of unlabeled samples to improve the performance of classification with a small number of labeled samples. Several strategies are included in the proposed method. First, in order to take the advantage of unlabeled samples, a data enhancement method based on the neighborhood nearest neighbor propagation method is proposed to enlarge the number of labeled samples. Second, to increase the role of central pixel in convolutional neural network classification based on the pixel, a spatial weighted method is proposed to increase the weight of central pixel features and weak the weight of other types of pixel features. Third, a specific deep model for PolSAR image classification (named Tc-CNN) is proposed, which can obtain more scale and deep polarization information to improve the classification results. The experimental results show that the proposed method achieves a much better performance than the existing classification methods when the number of labeled samples is few.https://ieeexplore.ieee.org/document/9172110/Convolutional neural network (CNN)polarimetric synthetic aperture radar (PolSAR)terrain classificationthree-channel convolutional neural network (Tc-CNN) |
| spellingShingle | Wenqiang Hua Wen Xie Xiaomin Jin Three-Channel Convolutional Neural Network for Polarimetric SAR Images Classification IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Convolutional neural network (CNN) polarimetric synthetic aperture radar (PolSAR) terrain classification three-channel convolutional neural network (Tc-CNN) |
| title | Three-Channel Convolutional Neural Network for Polarimetric SAR Images Classification |
| title_full | Three-Channel Convolutional Neural Network for Polarimetric SAR Images Classification |
| title_fullStr | Three-Channel Convolutional Neural Network for Polarimetric SAR Images Classification |
| title_full_unstemmed | Three-Channel Convolutional Neural Network for Polarimetric SAR Images Classification |
| title_short | Three-Channel Convolutional Neural Network for Polarimetric SAR Images Classification |
| title_sort | three channel convolutional neural network for polarimetric sar images classification |
| topic | Convolutional neural network (CNN) polarimetric synthetic aperture radar (PolSAR) terrain classification three-channel convolutional neural network (Tc-CNN) |
| url | https://ieeexplore.ieee.org/document/9172110/ |
| work_keys_str_mv | AT wenqianghua threechannelconvolutionalneuralnetworkforpolarimetricsarimagesclassification AT wenxie threechannelconvolutionalneuralnetworkforpolarimetricsarimagesclassification AT xiaominjin threechannelconvolutionalneuralnetworkforpolarimetricsarimagesclassification |