A python implementation of M2DP .
Project description
M2DP python
python implementation of the M2DP algorithm. Original repository can be found here.
Introduction:
Multiview 2D projection (M2DP) is a global descriptor of input point cloud.
Input:
data n*3 Point cloud. Each row is [x y z]
Output:
desM2DP 192*1 M2DP descriptor of the input cloud data
A 64*128 Signature matrix
Details of M2DP can be found in the following paper:
Li He, Xiaolong Wang and Hong Zhang, M2DP: A Novel 3D Point Cloud Descriptor and Its Application in Loop Closure Detection, IROS 2016.
Li He, Dept. of Computing Science, University of Alberta lhe2@ualberta.ca
Requirement
- Python 3.6
- Numpy
- Scikit-Learn
usage
Follow the below format to extract features from pointcloud:
from m2dp import M2DP
des,A=M2DP(point_cloud)
Acknowledgement
Thank @jubaer145 for your help in this project.
Reference
@inproceedings{he2016m2dp,
title={M2DP: A novel 3D point cloud descriptor and its application in loop closure detection},
author={He, Li and Wang, Xiaolong and Zhang, Hong},
booktitle={2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
pages={231--237},
year={2016},
organization={IEEE}
}
Copyright
See LICENSE for details.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
m2dp-0.1.2.tar.gz
(3.4 kB
view hashes)
Built Distribution
m2dp-0.1.2-py3-none-any.whl
(5.6 kB
view hashes)