Interpretable POLSAR Image Classification Based on Adaptive-Dimension Feature Space Decision Tree
Decision tree method has been applied to POLSAR image classification, due to its capability to interpret the scattering characteristics as well as good classification accuracy. Compared with popular machine learning classifiers, decision tree approach can explain the scattering process of certain ty...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9194017/ |
| _version_ | 1818847041065844736 |
|---|---|
| author | Qiang Yin Jianda Cheng Fan Zhang Yongsheng Zhou Luyi Shao Wen Hong |
| author_facet | Qiang Yin Jianda Cheng Fan Zhang Yongsheng Zhou Luyi Shao Wen Hong |
| author_sort | Qiang Yin |
| collection | DOAJ |
| description | Decision tree method has been applied to POLSAR image classification, due to its capability to interpret the scattering characteristics as well as good classification accuracy. Compared with popular machine learning classifiers, decision tree approach can explain the scattering process of certain type of targets by use of the polarimetric features at the tree nodes. Except the interpretability, decision tree approach could be transplanted to other data set without training process for the same terrain types, since the polarimetric features are inherently connected to the physical scattering properties. Currently, decision tree based classifiers, typically employ one single polarimetric feature at the nodes of the tree. The idea to increase the number of the polarization features at the decision tree node is expected to improve the classification result, which combine two or more polarimetric features to form a two or high dimension feature space. In this way, the classes which cannot be discriminated with one feature could possibly be separated with the space constructed by several features. However, it also inevitably leads to an increase in the computational burden. In fact, not all nodes require very high-dimensional feature space to achieve high classification precision. Therefore, in this article we proposed that the dimension of the feature space used in the decision tree nodes is adaptively changed from one to three, due to the separability of the classes under this node. The developed classification method is examined by the classical AIRSAR data in Flevoland area of the Netherlands, as well as GaoFen-3 data in Hulunbuir of China. The experiments show that the classification performance is superior to the fixed dimension feature decision tree methods, with less and reasonable computation time. Besides, the transferability of polarimetric features obtained by decision tree is preliminarily demonstrated in the application to another AIRSAR data. |
| first_indexed | 2024-12-19T05:55:08Z |
| format | Article |
| id | doaj.art-7077f84897d54790a3983521e82ed56b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T05:55:08Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7077f84897d54790a3983521e82ed56b2022-12-21T20:33:28ZengIEEEIEEE Access2169-35362020-01-01817382617383710.1109/ACCESS.2020.30231349194017Interpretable POLSAR Image Classification Based on Adaptive-Dimension Feature Space Decision TreeQiang Yin0https://orcid.org/0000-0002-8413-4756Jianda Cheng1https://orcid.org/0000-0002-2410-9778Fan Zhang2https://orcid.org/0000-0002-2058-2373Yongsheng Zhou3https://orcid.org/0000-0001-7261-7606Luyi Shao4Wen Hong5College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, ChinaCollege of Information Science and Technology, Beijing University of Chemical Technology, Beijing, ChinaCollege of Information Science and Technology, Beijing University of Chemical Technology, Beijing, ChinaCollege of Information Science and Technology, Beijing University of Chemical Technology, Beijing, ChinaCollege of Information Science and Engineering, Ocean University of China, Qingdao, ChinaChinese Academy of Sciences, Institute of Electronics, Beijing, ChinaDecision tree method has been applied to POLSAR image classification, due to its capability to interpret the scattering characteristics as well as good classification accuracy. Compared with popular machine learning classifiers, decision tree approach can explain the scattering process of certain type of targets by use of the polarimetric features at the tree nodes. Except the interpretability, decision tree approach could be transplanted to other data set without training process for the same terrain types, since the polarimetric features are inherently connected to the physical scattering properties. Currently, decision tree based classifiers, typically employ one single polarimetric feature at the nodes of the tree. The idea to increase the number of the polarization features at the decision tree node is expected to improve the classification result, which combine two or more polarimetric features to form a two or high dimension feature space. In this way, the classes which cannot be discriminated with one feature could possibly be separated with the space constructed by several features. However, it also inevitably leads to an increase in the computational burden. In fact, not all nodes require very high-dimensional feature space to achieve high classification precision. Therefore, in this article we proposed that the dimension of the feature space used in the decision tree nodes is adaptively changed from one to three, due to the separability of the classes under this node. The developed classification method is examined by the classical AIRSAR data in Flevoland area of the Netherlands, as well as GaoFen-3 data in Hulunbuir of China. The experiments show that the classification performance is superior to the fixed dimension feature decision tree methods, with less and reasonable computation time. Besides, the transferability of polarimetric features obtained by decision tree is preliminarily demonstrated in the application to another AIRSAR data.https://ieeexplore.ieee.org/document/9194017/Polarimetric SARfeature spacedecision treeterrain classification |
| spellingShingle | Qiang Yin Jianda Cheng Fan Zhang Yongsheng Zhou Luyi Shao Wen Hong Interpretable POLSAR Image Classification Based on Adaptive-Dimension Feature Space Decision Tree IEEE Access Polarimetric SAR feature space decision tree terrain classification |
| title | Interpretable POLSAR Image Classification Based on Adaptive-Dimension Feature Space Decision Tree |
| title_full | Interpretable POLSAR Image Classification Based on Adaptive-Dimension Feature Space Decision Tree |
| title_fullStr | Interpretable POLSAR Image Classification Based on Adaptive-Dimension Feature Space Decision Tree |
| title_full_unstemmed | Interpretable POLSAR Image Classification Based on Adaptive-Dimension Feature Space Decision Tree |
| title_short | Interpretable POLSAR Image Classification Based on Adaptive-Dimension Feature Space Decision Tree |
| title_sort | interpretable polsar image classification based on adaptive dimension feature space decision tree |
| topic | Polarimetric SAR feature space decision tree terrain classification |
| url | https://ieeexplore.ieee.org/document/9194017/ |
| work_keys_str_mv | AT qiangyin interpretablepolsarimageclassificationbasedonadaptivedimensionfeaturespacedecisiontree AT jiandacheng interpretablepolsarimageclassificationbasedonadaptivedimensionfeaturespacedecisiontree AT fanzhang interpretablepolsarimageclassificationbasedonadaptivedimensionfeaturespacedecisiontree AT yongshengzhou interpretablepolsarimageclassificationbasedonadaptivedimensionfeaturespacedecisiontree AT luyishao interpretablepolsarimageclassificationbasedonadaptivedimensionfeaturespacedecisiontree AT wenhong interpretablepolsarimageclassificationbasedonadaptivedimensionfeaturespacedecisiontree |