Hyperspectral image classification plays an important role in many remote sensing applications. However, the high-dimensional characteristics of hyperspectral images and the appropriate feature representations leave it with great challenges. In this article, these difficulties are addressed by developing a Spectrum Selection and Deep Feature Fusion based method. The proposed method has the following contributions: 1) reducing redundant information caused by high-dimension through spectrum selection which is just needed in training phase. 2) extracting the joint spectral-spatial features by deep feature fusion, which effectively improves the accuracy of scene classification. 3) increasing the network attention to scene classes of small number by the Class-Balanced loss function and overcome the influence of unbalanced distribution of experimental data. Experiments results in the Tiangong-1 natural scene images dataset (TG1-NSCD) demonstrate that the effectiveness of our algorithm and the OA is 17% higher than the baseline.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.