Refined Model-Based and Feature-Driven Extraction of Buildings from PolSAR Images
Polarimetric synthetic aperture radar (PolSAR) building extraction plays an important role in urban planning, disaster management, etc. In this paper, a building extraction method using refined model-based decomposition and robust scattering feature is proposed. On the one hand, the newly proposed r...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/11/11/1379 |
| _version_ | 1798018509429538816 |
|---|---|
| author | Hui Fan Sinong Quan Dahai Dai Xuesong Wang Shunping Xiao |
| author_facet | Hui Fan Sinong Quan Dahai Dai Xuesong Wang Shunping Xiao |
| author_sort | Hui Fan |
| collection | DOAJ |
| description | Polarimetric synthetic aperture radar (PolSAR) building extraction plays an important role in urban planning, disaster management, etc. In this paper, a building extraction method using refined model-based decomposition and robust scattering feature is proposed. On the one hand, the newly proposed refined five-component decomposition and its derived scattering powers are applied to detect the buildings. On the other hand, by combining the matrix elements and co-polarization correlation coefficient, a robust feature is proposed to discriminate buildings and non-buildings. Both these two preliminary extraction results are obtained through thresholding segmentation. Finally, they are fused via the HX Markov random fields so as to further improve the extraction accuracy. The performance of the proposed method is demonstrated and evaluated with Gaofen-3 and uninhabited aerial vehicle SAR full PolSAR data over different test sites. Outputs show that the proposed method outperforms other state-of-the-art methods and provides an overall accuracy of over 90%. |
| first_indexed | 2024-04-11T16:25:14Z |
| format | Article |
| id | doaj.art-17f1322b29ac44f8ae6107f7bac1693a |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-11T16:25:14Z |
| publishDate | 2019-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-17f1322b29ac44f8ae6107f7bac1693a2022-12-22T04:14:12ZengMDPI AGRemote Sensing2072-42922019-06-011111137910.3390/rs11111379rs11111379Refined Model-Based and Feature-Driven Extraction of Buildings from PolSAR ImagesHui Fan0Sinong Quan1Dahai Dai2Xuesong Wang3Shunping Xiao4State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, ChinaPolarimetric synthetic aperture radar (PolSAR) building extraction plays an important role in urban planning, disaster management, etc. In this paper, a building extraction method using refined model-based decomposition and robust scattering feature is proposed. On the one hand, the newly proposed refined five-component decomposition and its derived scattering powers are applied to detect the buildings. On the other hand, by combining the matrix elements and co-polarization correlation coefficient, a robust feature is proposed to discriminate buildings and non-buildings. Both these two preliminary extraction results are obtained through thresholding segmentation. Finally, they are fused via the HX Markov random fields so as to further improve the extraction accuracy. The performance of the proposed method is demonstrated and evaluated with Gaofen-3 and uninhabited aerial vehicle SAR full PolSAR data over different test sites. Outputs show that the proposed method outperforms other state-of-the-art methods and provides an overall accuracy of over 90%.https://www.mdpi.com/2072-4292/11/11/1379polarimetric synthetic aperture radar (PolSAR)building extractionrefined model-based decompositionrobust scattering featureHX Markov random fields |
| spellingShingle | Hui Fan Sinong Quan Dahai Dai Xuesong Wang Shunping Xiao Refined Model-Based and Feature-Driven Extraction of Buildings from PolSAR Images Remote Sensing polarimetric synthetic aperture radar (PolSAR) building extraction refined model-based decomposition robust scattering feature HX Markov random fields |
| title | Refined Model-Based and Feature-Driven Extraction of Buildings from PolSAR Images |
| title_full | Refined Model-Based and Feature-Driven Extraction of Buildings from PolSAR Images |
| title_fullStr | Refined Model-Based and Feature-Driven Extraction of Buildings from PolSAR Images |
| title_full_unstemmed | Refined Model-Based and Feature-Driven Extraction of Buildings from PolSAR Images |
| title_short | Refined Model-Based and Feature-Driven Extraction of Buildings from PolSAR Images |
| title_sort | refined model based and feature driven extraction of buildings from polsar images |
| topic | polarimetric synthetic aperture radar (PolSAR) building extraction refined model-based decomposition robust scattering feature HX Markov random fields |
| url | https://www.mdpi.com/2072-4292/11/11/1379 |
| work_keys_str_mv | AT huifan refinedmodelbasedandfeaturedrivenextractionofbuildingsfrompolsarimages AT sinongquan refinedmodelbasedandfeaturedrivenextractionofbuildingsfrompolsarimages AT dahaidai refinedmodelbasedandfeaturedrivenextractionofbuildingsfrompolsarimages AT xuesongwang refinedmodelbasedandfeaturedrivenextractionofbuildingsfrompolsarimages AT shunpingxiao refinedmodelbasedandfeaturedrivenextractionofbuildingsfrompolsarimages |