Laser & Optoelectronics Progress, Volume. 59, Issue 2, 0210014(2022)
Hyperspectral Image Classification Based on Modified DenseNet and Spatial Spectrum Attention Mechanism
Fig. 1. Modified three-dimensional convolution module
Fig. 2. Structure of the modified Dense_Layer
Fig. 3. Model of the spatial spectrum attention mechanism. (a) Channel attention mechanism; (b) spatial attention mechanism
Fig. 4. Structure of the Dense_Layer
Fig. 5. Structure of the MDSSAN model
Fig. 6. Indian Pines data set and label. (a) Indian Pines data set; (b) label
Fig. 7. Pavia University data set and label. (a) Pavia University data set; (b) label
Fig. 8. KSC data set and label. (a) KSC data set; (b) label
Fig. 9. Classification results of the Indian Pines data set. (a) Indian Pines data set; (b) label; (c) 2D_CNN; (d) 3D_CNN; (e) M3RCNN; (f) 3D_DenseNet; (g) MDSSAN
Fig. 10. Classification results of the Pavia University data set. (a) Pavia University data set; (b) label; (c) 2D_CNN;(d) 3D_CNN; (e) M3RCNN; (f) 3D_DenseNet; (g) MDSSAN
Fig. 11. Classification result diagram of the KSC data set. (a) KSC data set; (b) label; (c) 2D_CNN; (d) 3D_CNN; (e) M3RCNN; (f) 3D_DenseNet; (g) MDSSAN
|
|
|
|
|
|
|
Get Citation
Copy Citation Text
Xin Wang, Yanguo Fan. Hyperspectral Image Classification Based on Modified DenseNet and Spatial Spectrum Attention Mechanism[J]. Laser & Optoelectronics Progress, 2022, 59(2): 0210014
Category: Image Processing
Received: Jan. 21, 2021
Accepted: Mar. 15, 2021
Published Online: Dec. 23, 2021
The Author Email: Wang Xin (3166588225@qq.com)