Double Ghost Convolution Attention Mechanism Network: A Framework for Hyperspectral Reconstruction of a Single RGB Image
Current research on the reconstruction of hyperspectral images from RGB images using deep learning mainly focuses on learning complex mappings through deeper and wider convolutional neural networks (CNNs). However, the reconstruction accuracy of the hyperspectral image is not high and among other is...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/2/666 |
| _version_ | 1797409812687880192 |
|---|---|
| author | Wenju Wang Jiangwei Wang |
| author_facet | Wenju Wang Jiangwei Wang |
| author_sort | Wenju Wang |
| collection | DOAJ |
| description | Current research on the reconstruction of hyperspectral images from RGB images using deep learning mainly focuses on learning complex mappings through deeper and wider convolutional neural networks (CNNs). However, the reconstruction accuracy of the hyperspectral image is not high and among other issues the model for generating these images takes up too much storage space. In this study, we propose the double ghost convolution attention mechanism network (DGCAMN) framework for the reconstruction of a single RGB image to improve the accuracy of spectral reconstruction and reduce the storage occupied by the model. The proposed DGCAMN consists of a double ghost residual attention block (DGRAB) module and optimal nonlocal block (ONB). DGRAB module uses GhostNet and PRELU activation functions to reduce the calculation parameters of the data and reduce the storage size of the generative model. At the same time, the proposed double output feature Convolutional Block Attention Module (DOFCBAM) is used to capture the texture details on the feature map to maximize the content of the reconstructed hyperspectral image. In the proposed ONB, the Argmax activation function is used to obtain the region with the most abundant feature information and maximize the most useful feature parameters. This helps to improve the accuracy of spectral reconstruction. These contributions enable the DGCAMN framework to achieve the highest spectral accuracy with minimal storage consumption. The proposed method has been applied to the NTIRE 2020 dataset. Experimental results show that the proposed DGCAMN method outperforms the spectral accuracy reconstructed by advanced deep learning methods and greatly reduces storage consumption. |
| first_indexed | 2024-03-09T04:20:04Z |
| format | Article |
| id | doaj.art-68e0b2c8822b451680de34dff18680b4 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T04:20:04Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-68e0b2c8822b451680de34dff18680b42023-12-03T13:48:23ZengMDPI AGSensors1424-82202021-01-0121266610.3390/s21020666Double Ghost Convolution Attention Mechanism Network: A Framework for Hyperspectral Reconstruction of a Single RGB ImageWenju Wang0Jiangwei Wang1College of Communication and Art Design, University of Shanghai for Science and Technology, Shanghai 200093, ChinaCollege of Communication and Art Design, University of Shanghai for Science and Technology, Shanghai 200093, ChinaCurrent research on the reconstruction of hyperspectral images from RGB images using deep learning mainly focuses on learning complex mappings through deeper and wider convolutional neural networks (CNNs). However, the reconstruction accuracy of the hyperspectral image is not high and among other issues the model for generating these images takes up too much storage space. In this study, we propose the double ghost convolution attention mechanism network (DGCAMN) framework for the reconstruction of a single RGB image to improve the accuracy of spectral reconstruction and reduce the storage occupied by the model. The proposed DGCAMN consists of a double ghost residual attention block (DGRAB) module and optimal nonlocal block (ONB). DGRAB module uses GhostNet and PRELU activation functions to reduce the calculation parameters of the data and reduce the storage size of the generative model. At the same time, the proposed double output feature Convolutional Block Attention Module (DOFCBAM) is used to capture the texture details on the feature map to maximize the content of the reconstructed hyperspectral image. In the proposed ONB, the Argmax activation function is used to obtain the region with the most abundant feature information and maximize the most useful feature parameters. This helps to improve the accuracy of spectral reconstruction. These contributions enable the DGCAMN framework to achieve the highest spectral accuracy with minimal storage consumption. The proposed method has been applied to the NTIRE 2020 dataset. Experimental results show that the proposed DGCAMN method outperforms the spectral accuracy reconstructed by advanced deep learning methods and greatly reduces storage consumption.https://www.mdpi.com/1424-8220/21/2/666double ghost attention mechanism networkdouble output feature CBAMoptimal nonlocal block |
| spellingShingle | Wenju Wang Jiangwei Wang Double Ghost Convolution Attention Mechanism Network: A Framework for Hyperspectral Reconstruction of a Single RGB Image Sensors double ghost attention mechanism network double output feature CBAM optimal nonlocal block |
| title | Double Ghost Convolution Attention Mechanism Network: A Framework for Hyperspectral Reconstruction of a Single RGB Image |
| title_full | Double Ghost Convolution Attention Mechanism Network: A Framework for Hyperspectral Reconstruction of a Single RGB Image |
| title_fullStr | Double Ghost Convolution Attention Mechanism Network: A Framework for Hyperspectral Reconstruction of a Single RGB Image |
| title_full_unstemmed | Double Ghost Convolution Attention Mechanism Network: A Framework for Hyperspectral Reconstruction of a Single RGB Image |
| title_short | Double Ghost Convolution Attention Mechanism Network: A Framework for Hyperspectral Reconstruction of a Single RGB Image |
| title_sort | double ghost convolution attention mechanism network a framework for hyperspectral reconstruction of a single rgb image |
| topic | double ghost attention mechanism network double output feature CBAM optimal nonlocal block |
| url | https://www.mdpi.com/1424-8220/21/2/666 |
| work_keys_str_mv | AT wenjuwang doubleghostconvolutionattentionmechanismnetworkaframeworkforhyperspectralreconstructionofasinglergbimage AT jiangweiwang doubleghostconvolutionattentionmechanismnetworkaframeworkforhyperspectralreconstructionofasinglergbimage |