Urbanclassifier: a deep learning-based model for automated typology and temporal analysis of urban fabric across multiple spatial scales and viewpoints

HIGHLIGHTS

• What: In this research, BM-1 is designed to handle the morphological urban fabric classification tasks purely based on the local geometric features of the target urban fabric (land parcel), without considering spatial scale information or surrounding context. By comparing the performance of the three models-BM-MS (UC-1), UC-3 and UC-5-this study aims to demonstrate the effectiveness of considering urban fabric features across multiple viewpoints and to further assess how the number of viewpoints considered impacts the classification results. By comparing the classification performance of the BM-2 models in the experiment . . .
  

   

  

  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.