PolSAR Classification Using Contextual Based Locality Preserving Projection and Guided Filtering
Contextual feature extraction is studied for polarimetric synthetic aperture radar (PolSAR) image classification in this work. The contextual locality preserving projection (CLPP) method is proposed for generation of contextual feature cubes using limited training samples. The local information in n...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Iran Telecom Research Center
2021-06-01
|
| Series: | International Journal of Information and Communication Technology Research |
| Subjects: | |
| Online Access: | http://ijict.itrc.ac.ir/article-1-482-en.html |
| _version_ | 1811169256679669760 |
|---|---|
| author | Maryam Imani |
| author_facet | Maryam Imani |
| author_sort | Maryam Imani |
| collection | DOAJ |
| description | Contextual feature extraction is studied for polarimetric synthetic aperture radar (PolSAR) image classification in this work. The contextual locality preserving projection (CLPP) method is proposed for generation of contextual feature cubes using limited training samples. The local information in neighborhood regions is used to extend the training set by including the spatial information. Then, a supervised transform is applied to the polarimetric-contextual feature cube to reduce the data dimensionality while preserves the local structures and settles the samples belonging to the same class close together. Finally, a guided filter is applied to the classification map to degrade the speckle noise. The classification results on two real L-band PolSAR data from AIRSAR show superior performance of CLPP for PolSAR classification in small sample size situations. |
| first_indexed | 2024-04-10T16:39:21Z |
| format | Article |
| id | doaj.art-c762867694cb4024b5d1c726cca02671 |
| institution | Directory Open Access Journal |
| issn | 2251-6107 2783-4425 |
| language | English |
| last_indexed | 2024-04-10T16:39:21Z |
| publishDate | 2021-06-01 |
| publisher | Iran Telecom Research Center |
| record_format | Article |
| series | International Journal of Information and Communication Technology Research |
| spelling | doaj.art-c762867694cb4024b5d1c726cca026712023-02-08T08:00:07ZengIran Telecom Research CenterInternational Journal of Information and Communication Technology Research2251-61072783-44252021-06-011322938PolSAR Classification Using Contextual Based Locality Preserving Projection and Guided FilteringMaryam Imani0 Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran, Iran Contextual feature extraction is studied for polarimetric synthetic aperture radar (PolSAR) image classification in this work. The contextual locality preserving projection (CLPP) method is proposed for generation of contextual feature cubes using limited training samples. The local information in neighborhood regions is used to extend the training set by including the spatial information. Then, a supervised transform is applied to the polarimetric-contextual feature cube to reduce the data dimensionality while preserves the local structures and settles the samples belonging to the same class close together. Finally, a guided filter is applied to the classification map to degrade the speckle noise. The classification results on two real L-band PolSAR data from AIRSAR show superior performance of CLPP for PolSAR classification in small sample size situations.http://ijict.itrc.ac.ir/article-1-482-en.htmllocality preserving projectionspatial feature extractionclassificationpolarizationclassificationguided filter. |
| spellingShingle | Maryam Imani PolSAR Classification Using Contextual Based Locality Preserving Projection and Guided Filtering International Journal of Information and Communication Technology Research locality preserving projection spatial feature extraction classification polarization classification guided filter. |
| title | PolSAR Classification Using Contextual Based Locality Preserving Projection and Guided Filtering |
| title_full | PolSAR Classification Using Contextual Based Locality Preserving Projection and Guided Filtering |
| title_fullStr | PolSAR Classification Using Contextual Based Locality Preserving Projection and Guided Filtering |
| title_full_unstemmed | PolSAR Classification Using Contextual Based Locality Preserving Projection and Guided Filtering |
| title_short | PolSAR Classification Using Contextual Based Locality Preserving Projection and Guided Filtering |
| title_sort | polsar classification using contextual based locality preserving projection and guided filtering |
| topic | locality preserving projection spatial feature extraction classification polarization classification guided filter. |
| url | http://ijict.itrc.ac.ir/article-1-482-en.html |
| work_keys_str_mv | AT maryamimani polsarclassificationusingcontextualbasedlocalitypreservingprojectionandguidedfiltering |