Dynahull: density-centric dynamic point filtering in point clouds

HIGHLIGHTS

• What: In the study , the EMD is calculated using the ‘emd2` function from the Python Optimal Transport (POT) library, with maps uniformly downsampled to reduce computational requirements. The aim of this study is to improve the accuracy of indoors dynamic points filtering through density filtering. Considering the primary focus of the algorithm on indoor environments, the practicality of using 32 or 64 channel LiDARs may be questionable. The results of the study demonstrate improved performance of the methods compared to other state-of-theart techniques in all the presented metrics, namely, MAE, RMSE, 90th percentile error, CD . . .
  

   

  

  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.