Scene classification based on heterogeneous features of multi-source data

HIGHLIGHTS

• who: Chengjun Xu et al. from the School of Software, Jiangxi Normal University, Nanchang, China have published the research: Scene Classification Based on Heterogeneous Features of Multi-Source Data, in the Journal: (JOURNAL)
• what: To tackle the challenges the authors propose a novel model that integrates heterogeneous features of Firstly a multigranularity feature learning module is designed which can conduct uniform grid sampling of images to learn multi-granularity features. The authors propose a classification model based on 4 of 22 heterogeneous characteristics of multi-source data. The authors propose the Lie Group Fisher method . . .
  

   

  

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

  Thanks :)

  Username or E-mail:

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