Shape Adaptive Neighborhood Information-Based Semi-Supervised Learning for Hyperspectral Image Classification
Hyperspectral image (HSI) classification is an important research topic in detailed analysis of the Earth’s surface. However, the performance of the classification is often hampered by the high-dimensionality features and limited training samples of the HSIs which has fostered research about semi-su...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/18/2976 |
| _version_ | 1797553811317850112 |
|---|---|
| author | Yina Hu Ru An Benlin Wang Fei Xing Feng Ju |
| author_facet | Yina Hu Ru An Benlin Wang Fei Xing Feng Ju |
| author_sort | Yina Hu |
| collection | DOAJ |
| description | Hyperspectral image (HSI) classification is an important research topic in detailed analysis of the Earth’s surface. However, the performance of the classification is often hampered by the high-dimensionality features and limited training samples of the HSIs which has fostered research about semi-supervised learning (SSL). In this paper, we propose a shape adaptive neighborhood information (SANI) based SSL (SANI-SSL) method that takes full advantage of the adaptive spatial information to select valuable unlabeled samples in order to improve the classification ability. The improvement of the classification mainly relies on two aspects: (1) the improvement of the feature discriminability, which is accomplished by exploiting spectral-spatial information, and (2) the improvement of the training samples’ representativeness which is accomplished by exploiting the SANI for both labeled and unlabeled samples. First, the SANI of labeled samples is extracted, and the breaking ties (BT) method is used in order to select valuable unlabeled samples from the labeled samples’ neighborhood. Second, the SANI of unlabeled samples are also used to find more valuable samples, with the classifier combination method being used as a strategy to ensure confidence and the adaptive interval method used as a strategy to ensure informativeness. The experimental comparison results tested on three benchmark HSI datasets have demonstrated the significantly superior performance of our proposed method. |
| first_indexed | 2024-03-10T16:21:58Z |
| format | Article |
| id | doaj.art-d3fd1b2a2f7c4ea58f48642bb67a96a7 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T16:21:58Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-d3fd1b2a2f7c4ea58f48642bb67a96a72023-11-20T13:35:40ZengMDPI AGRemote Sensing2072-42922020-09-011218297610.3390/rs12182976Shape Adaptive Neighborhood Information-Based Semi-Supervised Learning for Hyperspectral Image ClassificationYina Hu0Ru An1Benlin Wang2Fei Xing3Feng Ju4College of Hydrology and Water Resources, Hohai University, Nanjing 211100, ChinaCollege of Hydrology and Water Resources, Hohai University, Nanjing 211100, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing 211100, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing 211100, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing 211100, ChinaHyperspectral image (HSI) classification is an important research topic in detailed analysis of the Earth’s surface. However, the performance of the classification is often hampered by the high-dimensionality features and limited training samples of the HSIs which has fostered research about semi-supervised learning (SSL). In this paper, we propose a shape adaptive neighborhood information (SANI) based SSL (SANI-SSL) method that takes full advantage of the adaptive spatial information to select valuable unlabeled samples in order to improve the classification ability. The improvement of the classification mainly relies on two aspects: (1) the improvement of the feature discriminability, which is accomplished by exploiting spectral-spatial information, and (2) the improvement of the training samples’ representativeness which is accomplished by exploiting the SANI for both labeled and unlabeled samples. First, the SANI of labeled samples is extracted, and the breaking ties (BT) method is used in order to select valuable unlabeled samples from the labeled samples’ neighborhood. Second, the SANI of unlabeled samples are also used to find more valuable samples, with the classifier combination method being used as a strategy to ensure confidence and the adaptive interval method used as a strategy to ensure informativeness. The experimental comparison results tested on three benchmark HSI datasets have demonstrated the significantly superior performance of our proposed method.https://www.mdpi.com/2072-4292/12/18/2976hyperspectral images classificationshape adaptivesemi-supervised learningactive learningspectral-spatial information |
| spellingShingle | Yina Hu Ru An Benlin Wang Fei Xing Feng Ju Shape Adaptive Neighborhood Information-Based Semi-Supervised Learning for Hyperspectral Image Classification Remote Sensing hyperspectral images classification shape adaptive semi-supervised learning active learning spectral-spatial information |
| title | Shape Adaptive Neighborhood Information-Based Semi-Supervised Learning for Hyperspectral Image Classification |
| title_full | Shape Adaptive Neighborhood Information-Based Semi-Supervised Learning for Hyperspectral Image Classification |
| title_fullStr | Shape Adaptive Neighborhood Information-Based Semi-Supervised Learning for Hyperspectral Image Classification |
| title_full_unstemmed | Shape Adaptive Neighborhood Information-Based Semi-Supervised Learning for Hyperspectral Image Classification |
| title_short | Shape Adaptive Neighborhood Information-Based Semi-Supervised Learning for Hyperspectral Image Classification |
| title_sort | shape adaptive neighborhood information based semi supervised learning for hyperspectral image classification |
| topic | hyperspectral images classification shape adaptive semi-supervised learning active learning spectral-spatial information |
| url | https://www.mdpi.com/2072-4292/12/18/2976 |
| work_keys_str_mv | AT yinahu shapeadaptiveneighborhoodinformationbasedsemisupervisedlearningforhyperspectralimageclassification AT ruan shapeadaptiveneighborhoodinformationbasedsemisupervisedlearningforhyperspectralimageclassification AT benlinwang shapeadaptiveneighborhoodinformationbasedsemisupervisedlearningforhyperspectralimageclassification AT feixing shapeadaptiveneighborhoodinformationbasedsemisupervisedlearningforhyperspectralimageclassification AT fengju shapeadaptiveneighborhoodinformationbasedsemisupervisedlearningforhyperspectralimageclassification |