Superpixel-Based Hybrid Discriminative Random Field for Fast PolSAR Image Classification
Performance of the powerful discriminative random field (DRF) model for image processing and analysis is easily affected by the inherent speckle noise and the time-consuming iteration. Therefore, in this paper, a superpixel-based hybrid DRF (sp-HDRF) model is proposed for fast polarimetric synthetic...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8641272/ |
| _version_ | 1818619199264653312 |
|---|---|
| author | Wanying Song Ming Li Peng Zhang Yan Wu Xiaofeng Tan |
| author_facet | Wanying Song Ming Li Peng Zhang Yan Wu Xiaofeng Tan |
| author_sort | Wanying Song |
| collection | DOAJ |
| description | Performance of the powerful discriminative random field (DRF) model for image processing and analysis is easily affected by the inherent speckle noise and the time-consuming iteration. Therefore, in this paper, a superpixel-based hybrid DRF (sp-HDRF) model is proposed for fast polarimetric synthetic aperture radar (PolSAR) image classification. The sp-HDRF model realizes the classification by two steps. First, the simple linear iterative clustering algorithm, which is modified by introducing the ratio of exponentially weighted averages operator, is utilized to obtain a superpixel graph with more accurate edge locations. Second, the conditional posterior distribution and the inference formula of the sp-HDRF model are derived on the superpixel graph, which is a generalization of a DRF model on the pixel. Then, the sp-HDRF model is applied to implement classification. Finally, the sp-HDRF model has the fusion of the polarimetric scattering features, the statistics, and the spatial relationships of the image. The experimental results on the real PolSAR images demonstrate the effectiveness of the sp-HDRF model and illustrate that it can provide stronger noise immunity, obtain smoother homogeneous areas in classification, and enhance the computational efficiency simultaneously. |
| first_indexed | 2024-12-16T17:33:41Z |
| format | Article |
| id | doaj.art-e5b60ab91b5542eb86daec1870677973 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T17:33:41Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e5b60ab91b5542eb86daec18706779732022-12-21T22:22:52ZengIEEEIEEE Access2169-35362019-01-017245472455810.1109/ACCESS.2019.28991168641272Superpixel-Based Hybrid Discriminative Random Field for Fast PolSAR Image ClassificationWanying Song0https://orcid.org/0000-0002-3777-067XMing Li1Peng Zhang2Yan Wu3Xiaofeng Tan4National Laboratory of Radar Signal Processing, Xidian University, Xi’an, ChinaNational Laboratory of Radar Signal Processing, Xidian University, Xi’an, ChinaNational Laboratory of Radar Signal Processing, Xidian University, Xi’an, ChinaRemote Sensing Image Processing and Fusion Group, School of Electronics Engineering, Xidian University, Xi’an, ChinaNational Laboratory of Radar Signal Processing, Xidian University, Xi’an, ChinaPerformance of the powerful discriminative random field (DRF) model for image processing and analysis is easily affected by the inherent speckle noise and the time-consuming iteration. Therefore, in this paper, a superpixel-based hybrid DRF (sp-HDRF) model is proposed for fast polarimetric synthetic aperture radar (PolSAR) image classification. The sp-HDRF model realizes the classification by two steps. First, the simple linear iterative clustering algorithm, which is modified by introducing the ratio of exponentially weighted averages operator, is utilized to obtain a superpixel graph with more accurate edge locations. Second, the conditional posterior distribution and the inference formula of the sp-HDRF model are derived on the superpixel graph, which is a generalization of a DRF model on the pixel. Then, the sp-HDRF model is applied to implement classification. Finally, the sp-HDRF model has the fusion of the polarimetric scattering features, the statistics, and the spatial relationships of the image. The experimental results on the real PolSAR images demonstrate the effectiveness of the sp-HDRF model and illustrate that it can provide stronger noise immunity, obtain smoother homogeneous areas in classification, and enhance the computational efficiency simultaneously.https://ieeexplore.ieee.org/document/8641272/Polarimetric synthetic aperture radar (PolSAR)image classificationdiscriminative random fields (DRF)superpixel |
| spellingShingle | Wanying Song Ming Li Peng Zhang Yan Wu Xiaofeng Tan Superpixel-Based Hybrid Discriminative Random Field for Fast PolSAR Image Classification IEEE Access Polarimetric synthetic aperture radar (PolSAR) image classification discriminative random fields (DRF) superpixel |
| title | Superpixel-Based Hybrid Discriminative Random Field for Fast PolSAR Image Classification |
| title_full | Superpixel-Based Hybrid Discriminative Random Field for Fast PolSAR Image Classification |
| title_fullStr | Superpixel-Based Hybrid Discriminative Random Field for Fast PolSAR Image Classification |
| title_full_unstemmed | Superpixel-Based Hybrid Discriminative Random Field for Fast PolSAR Image Classification |
| title_short | Superpixel-Based Hybrid Discriminative Random Field for Fast PolSAR Image Classification |
| title_sort | superpixel based hybrid discriminative random field for fast polsar image classification |
| topic | Polarimetric synthetic aperture radar (PolSAR) image classification discriminative random fields (DRF) superpixel |
| url | https://ieeexplore.ieee.org/document/8641272/ |
| work_keys_str_mv | AT wanyingsong superpixelbasedhybriddiscriminativerandomfieldforfastpolsarimageclassification AT mingli superpixelbasedhybriddiscriminativerandomfieldforfastpolsarimageclassification AT pengzhang superpixelbasedhybriddiscriminativerandomfieldforfastpolsarimageclassification AT yanwu superpixelbasedhybriddiscriminativerandomfieldforfastpolsarimageclassification AT xiaofengtan superpixelbasedhybriddiscriminativerandomfieldforfastpolsarimageclassification |