Densely Connected Pyramidal Dilated Convolutional Network for Hyperspectral Image Classification
Recently, with the extensive application of deep learning techniques in the hyperspectral image (HSI) field, particularly convolutional neural network (CNN), the research of HSI classification has stepped into a new stage. To avoid the problem that the receptive field of naive convolution is small,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/17/3396 |
| _version_ | 1797520882895159296 |
|---|---|
| author | Feng Zhao Junjie Zhang Zhe Meng Hanqiang Liu |
| author_facet | Feng Zhao Junjie Zhang Zhe Meng Hanqiang Liu |
| author_sort | Feng Zhao |
| collection | DOAJ |
| description | Recently, with the extensive application of deep learning techniques in the hyperspectral image (HSI) field, particularly convolutional neural network (CNN), the research of HSI classification has stepped into a new stage. To avoid the problem that the receptive field of naive convolution is small, the dilated convolution is introduced into the field of HSI classification. However, the dilated convolution usually generates blind spots in the receptive field, resulting in discontinuous spatial information obtained. In order to solve the above problem, a densely connected pyramidal dilated convolutional network (PDCNet) is proposed in this paper. Firstly, a pyramidal dilated convolutional (PDC) layer integrates different numbers of sub-dilated convolutional layers is proposed, where the dilated factor of the sub-dilated convolution increases exponentially, achieving multi-sacle receptive fields. Secondly, the number of sub-dilated convolutional layers increases in a pyramidal pattern with the depth of the network, thereby capturing more comprehensive hyperspectral information in the receptive field. Furthermore, a feature fusion mechanism combining pixel-by-pixel addition and channel stacking is adopted to extract more abstract spectral–spatial features. Finally, in order to reuse the features of the previous layers more effectively, dense connections are applied in densely pyramidal dilated convolutional (DPDC) blocks. Experiments on three well-known HSI datasets indicate that PDCNet proposed in this paper has good classification performance compared with other popular models. |
| first_indexed | 2024-03-10T08:04:53Z |
| format | Article |
| id | doaj.art-651eeba60a2a4a129d01f50c10221f87 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T08:04:53Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-651eeba60a2a4a129d01f50c10221f872023-11-22T11:08:16ZengMDPI AGRemote Sensing2072-42922021-08-011317339610.3390/rs13173396Densely Connected Pyramidal Dilated Convolutional Network for Hyperspectral Image ClassificationFeng Zhao0Junjie Zhang1Zhe Meng2Hanqiang Liu3School of Communications and Information Engineering (School of Artificial Intelligence), Xi’an University of Posts and Telecommunications, Xi’an 710121, ChinaSchool of Communications and Information Engineering (School of Artificial Intelligence), Xi’an University of Posts and Telecommunications, Xi’an 710121, ChinaSchool of Communications and Information Engineering (School of Artificial Intelligence), Xi’an University of Posts and Telecommunications, Xi’an 710121, ChinaSchool of Computer Science, Shaanxi Normal University, Xi’an 710119, ChinaRecently, with the extensive application of deep learning techniques in the hyperspectral image (HSI) field, particularly convolutional neural network (CNN), the research of HSI classification has stepped into a new stage. To avoid the problem that the receptive field of naive convolution is small, the dilated convolution is introduced into the field of HSI classification. However, the dilated convolution usually generates blind spots in the receptive field, resulting in discontinuous spatial information obtained. In order to solve the above problem, a densely connected pyramidal dilated convolutional network (PDCNet) is proposed in this paper. Firstly, a pyramidal dilated convolutional (PDC) layer integrates different numbers of sub-dilated convolutional layers is proposed, where the dilated factor of the sub-dilated convolution increases exponentially, achieving multi-sacle receptive fields. Secondly, the number of sub-dilated convolutional layers increases in a pyramidal pattern with the depth of the network, thereby capturing more comprehensive hyperspectral information in the receptive field. Furthermore, a feature fusion mechanism combining pixel-by-pixel addition and channel stacking is adopted to extract more abstract spectral–spatial features. Finally, in order to reuse the features of the previous layers more effectively, dense connections are applied in densely pyramidal dilated convolutional (DPDC) blocks. Experiments on three well-known HSI datasets indicate that PDCNet proposed in this paper has good classification performance compared with other popular models.https://www.mdpi.com/2072-4292/13/17/3396hyperspectral image classificationconvolutional neural networkdilated convolutiondense connection |
| spellingShingle | Feng Zhao Junjie Zhang Zhe Meng Hanqiang Liu Densely Connected Pyramidal Dilated Convolutional Network for Hyperspectral Image Classification Remote Sensing hyperspectral image classification convolutional neural network dilated convolution dense connection |
| title | Densely Connected Pyramidal Dilated Convolutional Network for Hyperspectral Image Classification |
| title_full | Densely Connected Pyramidal Dilated Convolutional Network for Hyperspectral Image Classification |
| title_fullStr | Densely Connected Pyramidal Dilated Convolutional Network for Hyperspectral Image Classification |
| title_full_unstemmed | Densely Connected Pyramidal Dilated Convolutional Network for Hyperspectral Image Classification |
| title_short | Densely Connected Pyramidal Dilated Convolutional Network for Hyperspectral Image Classification |
| title_sort | densely connected pyramidal dilated convolutional network for hyperspectral image classification |
| topic | hyperspectral image classification convolutional neural network dilated convolution dense connection |
| url | https://www.mdpi.com/2072-4292/13/17/3396 |
| work_keys_str_mv | AT fengzhao denselyconnectedpyramidaldilatedconvolutionalnetworkforhyperspectralimageclassification AT junjiezhang denselyconnectedpyramidaldilatedconvolutionalnetworkforhyperspectralimageclassification AT zhemeng denselyconnectedpyramidaldilatedconvolutionalnetworkforhyperspectralimageclassification AT hanqiangliu denselyconnectedpyramidaldilatedconvolutionalnetworkforhyperspectralimageclassification |