Hyperspectral Image Spectral–Spatial Classification Method Based on Deep Adaptive Feature Fusion
Convolutional neural networks (CNNs) have been widely used in hyperspectral image (HSI) classification. Many algorithms focus on the deep extraction of a single kind of feature to improve classification. There have been few studies on the deep extraction of two or more kinds of fusion features and t...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/4/746 |
| _version_ | 1797396169206267904 |
|---|---|
| author | Caihong Mu Yijin Liu Yi Liu |
| author_facet | Caihong Mu Yijin Liu Yi Liu |
| author_sort | Caihong Mu |
| collection | DOAJ |
| description | Convolutional neural networks (CNNs) have been widely used in hyperspectral image (HSI) classification. Many algorithms focus on the deep extraction of a single kind of feature to improve classification. There have been few studies on the deep extraction of two or more kinds of fusion features and the combination of spatial and spectral features for classification. The authors of this paper propose an HSI spectral–spatial classification method based on deep adaptive feature fusion (SSDF). This method first implements the deep adaptive fusion of two hyperspectral features, and then it performs spectral–spatial classification on the fused features. In SSDF, a U-shaped deep network model with the principal component features as the model input and the edge features as the model label is designed to adaptively fuse two kinds of different features. One comprises the edge features of the HSIs extracted by the guided filter, and the other comprises the principal component features obtained by dimensionality reduction of HSIs using principal component analysis. The fused new features are input into a multi-scale and multi-level feature extraction model for further extraction of deep features, which are then combined with the spectral features extracted by the long short-term memory (LSTM) model for classification. The experimental results on three datasets demonstrated that the performance of the proposed SSDF was superior to several state-of-the-art methods. Additionally, SSDF was found to be able to perform best as the number of training samples decreased sharply, and it could also obtain a high classification accuracy for categories with few samples. |
| first_indexed | 2024-03-09T00:47:23Z |
| format | Article |
| id | doaj.art-2cac7596e38d4503a628d171e757001c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T00:47:23Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2cac7596e38d4503a628d171e757001c2023-12-11T17:27:20ZengMDPI AGRemote Sensing2072-42922021-02-0113474610.3390/rs13040746Hyperspectral Image Spectral–Spatial Classification Method Based on Deep Adaptive Feature FusionCaihong Mu0Yijin Liu1Yi Liu2Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Collaborative Innovation Center of Quantum Information of Shaanxi Province, International Research Center for Intelligent Perception and Computation, Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Collaborative Innovation Center of Quantum Information of Shaanxi Province, International Research Center for Intelligent Perception and Computation, Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaSchool of Electronic Engineering, Xidian University, Xi’an 710071, ChinaConvolutional neural networks (CNNs) have been widely used in hyperspectral image (HSI) classification. Many algorithms focus on the deep extraction of a single kind of feature to improve classification. There have been few studies on the deep extraction of two or more kinds of fusion features and the combination of spatial and spectral features for classification. The authors of this paper propose an HSI spectral–spatial classification method based on deep adaptive feature fusion (SSDF). This method first implements the deep adaptive fusion of two hyperspectral features, and then it performs spectral–spatial classification on the fused features. In SSDF, a U-shaped deep network model with the principal component features as the model input and the edge features as the model label is designed to adaptively fuse two kinds of different features. One comprises the edge features of the HSIs extracted by the guided filter, and the other comprises the principal component features obtained by dimensionality reduction of HSIs using principal component analysis. The fused new features are input into a multi-scale and multi-level feature extraction model for further extraction of deep features, which are then combined with the spectral features extracted by the long short-term memory (LSTM) model for classification. The experimental results on three datasets demonstrated that the performance of the proposed SSDF was superior to several state-of-the-art methods. Additionally, SSDF was found to be able to perform best as the number of training samples decreased sharply, and it could also obtain a high classification accuracy for categories with few samples.https://www.mdpi.com/2072-4292/13/4/746hyperspectral image classificationadaptive feature fusionmulti-feature fusionmulti-scale and multi-level feature extraction model |
| spellingShingle | Caihong Mu Yijin Liu Yi Liu Hyperspectral Image Spectral–Spatial Classification Method Based on Deep Adaptive Feature Fusion Remote Sensing hyperspectral image classification adaptive feature fusion multi-feature fusion multi-scale and multi-level feature extraction model |
| title | Hyperspectral Image Spectral–Spatial Classification Method Based on Deep Adaptive Feature Fusion |
| title_full | Hyperspectral Image Spectral–Spatial Classification Method Based on Deep Adaptive Feature Fusion |
| title_fullStr | Hyperspectral Image Spectral–Spatial Classification Method Based on Deep Adaptive Feature Fusion |
| title_full_unstemmed | Hyperspectral Image Spectral–Spatial Classification Method Based on Deep Adaptive Feature Fusion |
| title_short | Hyperspectral Image Spectral–Spatial Classification Method Based on Deep Adaptive Feature Fusion |
| title_sort | hyperspectral image spectral spatial classification method based on deep adaptive feature fusion |
| topic | hyperspectral image classification adaptive feature fusion multi-feature fusion multi-scale and multi-level feature extraction model |
| url | https://www.mdpi.com/2072-4292/13/4/746 |
| work_keys_str_mv | AT caihongmu hyperspectralimagespectralspatialclassificationmethodbasedondeepadaptivefeaturefusion AT yijinliu hyperspectralimagespectralspatialclassificationmethodbasedondeepadaptivefeaturefusion AT yiliu hyperspectralimagespectralspatialclassificationmethodbasedondeepadaptivefeaturefusion |