Skip to content

Pytorch implementation of Analysis of voxel-based 3D object detection methods efficiency for real-time embedded systems paper

License

Notifications You must be signed in to change notification settings

iliiliiliili/tanet-near-far

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

40 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Analysis of voxel-based 3D object detection methods efficiency for real-time embedded systems

This is a code that allows to reproduce results of the Analysis of voxel-based 3D object detection methods efficiency for real-time embedded systems paper.

The training configurations for PointPillars and TANet models can be found in pointpillars_with_TANet/second/configs/{pointpillars|tanet}/car/near_far/

Our code is based on TANet, which is based on PointPillars and SECOND.

Video, describing results of the paper can be found here.

If you use this work for your research, you can cite it as:

@INPROCEEDINGS{oleksiienko2021voxel3od,
  author={Oleksiienko, Illia and Iosifidis, Alexandros},
  booktitle={2021 International Conference on Emerging Techniques in Computational Intelligence (ICETCI)}, 
  title={Analysis of voxel-based 3D object detection methods efficiency for real-time embedded systems}, 
  year={2021},
  pages={59-64}
}

About

Pytorch implementation of Analysis of voxel-based 3D object detection methods efficiency for real-time embedded systems paper

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published