Hyperspectral Image Classification Method Based on Multi-scale Densenet and Bi-RNN Joint Network
| Autor: | Shaoquan Zhang, Jun Li, Lianhui Liang |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | IOP Conference Series: Earth and Environmental Science. 783:012087 |
| ISSN: | 1755-1315 1755-1307 |
| DOI: | 10.1088/1755-1315/783/1/012087 |
| Popis: | With the depth of the Convolutional neural network(CNN) increases, CNN may lead to the problem of gradient disappearance. Simultaneously, single scale convolutional kernel may not reflect the complex spatial structural information in hyperspectral image(HSI). In addition, the CNN based approach regards the spectral band data on a single pixel of the HSI as a disordered high dimensional vector for processing, which does not meet the characteristics of the spectral band data. To tackle these aforementioned issues, a novel classification approach based on multi-scale densely connected convolutional network(Densenet) and bi-direction recurrent neural network(Bi-RNN) with attention framework is introduced in this study. Specifically, multi-scale Densenet is exploited to fully extract the multiple scales complex spatial structural information and utilize the strong complementary yet correlated spatial feature information between convolution layers, and Bi-RNN with attention is designed to obtain inner spectral correlations within a continuous spectrum. For comparison and verifying the effectiveness of our proposed method, we test the proposed method with nine other recently proposed methods on Salinas dataset, and the experimental results demonstrate that the proposed method can sufficiently exploit spectral and spatial information and outperforms other competitive methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|