Hyperspectral Image Classification Based on Superpixel Pooling Convolutional Neural Network with Transfer Learning
Deep learning-based hyperspectral image (HSI) classification has attracted more and more attention because of its excellent classification ability. Generally, the outstanding performance of these methods mainly depends on a large number of labeled samples. Therefore, it still remains an ongoing chal...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/5/930 |
| _version_ | 1797415754678665216 |
|---|---|
| author | Fuding Xie Quanshan Gao Cui Jin Fengxia Zhao |
| author_facet | Fuding Xie Quanshan Gao Cui Jin Fengxia Zhao |
| author_sort | Fuding Xie |
| collection | DOAJ |
| description | Deep learning-based hyperspectral image (HSI) classification has attracted more and more attention because of its excellent classification ability. Generally, the outstanding performance of these methods mainly depends on a large number of labeled samples. Therefore, it still remains an ongoing challenge how to integrate spatial structure information into these frameworks to classify the HSI with limited training samples. In this study, an effective spectral-spatial HSI classification scheme is proposed based on superpixel pooling convolutional neural network with transfer learning (SP-CNN). The suggested method includes three stages. The first part consists of convolution and pooling operation, which is a down-sampling process to extract the main spectral features of an HSI. The second part is composed of up-sampling and superpixel (homogeneous regions with adaptive shape and size) pooling to explore the spatial structure information of an HSI. Finally, the hyperspectral data with each superpixel as a basic input rather than a pixel are fed to fully connected neural network. In this method, the spectral and spatial information is effectively fused by using superpixel pooling technique. The use of popular transfer learning technology in the proposed classification framework significantly improves the training efficiency of SP-CNN. To evaluate the effectiveness of the SP-CNN, extensive experiments were conducted on three common real HSI datasets acquired from different sensors. With 30 labeled pixels per class, the overall classification accuracy provided by this method on three benchmarks all exceeded 93%, which was at least 4.55% higher than that of several state-of-the-art approaches. Experimental and comparative results prove that the proposed algorithm can effectively classify the HSI with limited training labels. |
| first_indexed | 2024-03-09T05:54:09Z |
| format | Article |
| id | doaj.art-43af1c8084bc40baa5e322950304c29b |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T05:54:09Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-43af1c8084bc40baa5e322950304c29b2023-12-03T12:15:09ZengMDPI AGRemote Sensing2072-42922021-03-0113593010.3390/rs13050930Hyperspectral Image Classification Based on Superpixel Pooling Convolutional Neural Network with Transfer LearningFuding Xie0Quanshan Gao1Cui Jin2Fengxia Zhao3School of Geography, Liaoning Normal University, Dalian 116029, ChinaSchool of Geography, Liaoning Normal University, Dalian 116029, ChinaSchool of Geography, Liaoning Normal University, Dalian 116029, ChinaDepartment of Information Engineering, Qinhuangdao Vocational and Technical College, Qinhuangdao 116600, ChinaDeep learning-based hyperspectral image (HSI) classification has attracted more and more attention because of its excellent classification ability. Generally, the outstanding performance of these methods mainly depends on a large number of labeled samples. Therefore, it still remains an ongoing challenge how to integrate spatial structure information into these frameworks to classify the HSI with limited training samples. In this study, an effective spectral-spatial HSI classification scheme is proposed based on superpixel pooling convolutional neural network with transfer learning (SP-CNN). The suggested method includes three stages. The first part consists of convolution and pooling operation, which is a down-sampling process to extract the main spectral features of an HSI. The second part is composed of up-sampling and superpixel (homogeneous regions with adaptive shape and size) pooling to explore the spatial structure information of an HSI. Finally, the hyperspectral data with each superpixel as a basic input rather than a pixel are fed to fully connected neural network. In this method, the spectral and spatial information is effectively fused by using superpixel pooling technique. The use of popular transfer learning technology in the proposed classification framework significantly improves the training efficiency of SP-CNN. To evaluate the effectiveness of the SP-CNN, extensive experiments were conducted on three common real HSI datasets acquired from different sensors. With 30 labeled pixels per class, the overall classification accuracy provided by this method on three benchmarks all exceeded 93%, which was at least 4.55% higher than that of several state-of-the-art approaches. Experimental and comparative results prove that the proposed algorithm can effectively classify the HSI with limited training labels.https://www.mdpi.com/2072-4292/13/5/930hyperspectral imageclassificationsuperpixelconvolutional neural networktransfer learningdeep learning |
| spellingShingle | Fuding Xie Quanshan Gao Cui Jin Fengxia Zhao Hyperspectral Image Classification Based on Superpixel Pooling Convolutional Neural Network with Transfer Learning Remote Sensing hyperspectral image classification superpixel convolutional neural network transfer learning deep learning |
| title | Hyperspectral Image Classification Based on Superpixel Pooling Convolutional Neural Network with Transfer Learning |
| title_full | Hyperspectral Image Classification Based on Superpixel Pooling Convolutional Neural Network with Transfer Learning |
| title_fullStr | Hyperspectral Image Classification Based on Superpixel Pooling Convolutional Neural Network with Transfer Learning |
| title_full_unstemmed | Hyperspectral Image Classification Based on Superpixel Pooling Convolutional Neural Network with Transfer Learning |
| title_short | Hyperspectral Image Classification Based on Superpixel Pooling Convolutional Neural Network with Transfer Learning |
| title_sort | hyperspectral image classification based on superpixel pooling convolutional neural network with transfer learning |
| topic | hyperspectral image classification superpixel convolutional neural network transfer learning deep learning |
| url | https://www.mdpi.com/2072-4292/13/5/930 |
| work_keys_str_mv | AT fudingxie hyperspectralimageclassificationbasedonsuperpixelpoolingconvolutionalneuralnetworkwithtransferlearning AT quanshangao hyperspectralimageclassificationbasedonsuperpixelpoolingconvolutionalneuralnetworkwithtransferlearning AT cuijin hyperspectralimageclassificationbasedonsuperpixelpoolingconvolutionalneuralnetworkwithtransferlearning AT fengxiazhao hyperspectralimageclassificationbasedonsuperpixelpoolingconvolutionalneuralnetworkwithtransferlearning |