Acta Photonica Sinica, Volume. 50, Issue 9, 0910001(2021)
Hyperspectral Images Classification Method Based on 3D Octave Convolution and Bi-RNN Attention Network
Fig. 1. Flow of framework for 3D Octave convolution and Bi-RNN attention network
Fig. 2. Flow of 3D Octave convolution network
Fig. 3. Structure of Bi-RNN network
Fig. 4. Structure of Bi-RNN attention network
Fig. 5. The whole structure diagram of 3D Octave convolution and Bi-RNN attention network
Fig. 6. Classification maps of different methods on the Pavia University dataset
Fig. 7. Partial enlargement comparison of classification maps on the Pavia University dataset
Fig. 8. Classification maps of different methods on the Botswana dataset
Fig. 9. Partial enlargement comparison of classification maps on the Botswana dataset
|
|
|
|
|
|
|
|
|
Get Citation
Copy Citation Text
Lianhui LIANG, Jun LI, Shaoquan ZHANG. Hyperspectral Images Classification Method Based on 3D Octave Convolution and Bi-RNN Attention Network[J]. Acta Photonica Sinica, 2021, 50(9): 0910001
Category: Image Processing
Received: Jan. 4, 2021
Accepted: May. 6, 2021
Published Online: Oct. 22, 2021
The Author Email: ZHANG Shaoquan (zhangshaoquan1@163.com)