Extended subspace projection upon sample augmentation based on global spatial and local spectral similarity for hyperspectral imagery classification

HIGHLIGHTS

• who: -Hyperspectral remote sensing and colleagues from the IVEXPERIMENTAL RESULTS AND ANALYSIS In this section, ESSA-GLSC is evaluated via three real hyperspectral datasets from different sensors, of which the details are provided in Section IV-A. The related parameters of the sample augmentation stage, extended subspace projection and NADRC are illustrated in Section IV-B. For comparison, the Support Vector Machines (SVM), SRC, Support Vector Machines-Markov Random Field (SVM-MRF) and joint SRC (JSRC) [53] are used to compare the performance of the proposed method. Moreover, labeled sample size and the number of dimensions is . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.