https://github.com/ait-assistive-autonomous-systems/3d_nonrigid_tricubic_pointcloud_registration

Non-rigid ICP-like point cloud registration algorithm using piece-wise tricubic polynomials as transformation model.

https://github.com/ait-assistive-autonomous-systems/3d_nonrigid_tricubic_pointcloud_registration

Science Score: 57.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 1 DOI reference(s) in README
  • Academic publication links
    Links to: mdpi.com
  • Academic email domains
  • Institutional organization owner
    Organization ait-assistive-autonomous-systems has institutional domain (www.ait.ac.at)
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (11.8%) to scientific vocabulary

Keywords

computer-vision icp lidar pointcloud registration robotics
Last synced: 6 months ago · JSON representation

Repository

Non-rigid ICP-like point cloud registration algorithm using piece-wise tricubic polynomials as transformation model.

Basic Info
  • Host: GitHub
  • Owner: AIT-Assistive-Autonomous-Systems
  • License: mit
  • Language: C++
  • Default Branch: main
  • Homepage:
  • Size: 7.83 MB
Statistics
  • Stars: 19
  • Watchers: 2
  • Forks: 7
  • Open Issues: 6
  • Releases: 0
Topics
computer-vision icp lidar pointcloud registration robotics
Created over 2 years ago · Last pushed 6 months ago
Metadata Files
Readme License

README.md

3D Non-Rigid Tricubic Point Cloud Registration

Method

This is an implementation of the method described in the paper "Non-rigid point cloud registration using piece-wise tricubic polynomials as transformation model".

This method can be used to register two 3D point clouds which are related by a non-rigid transformation. In other words, when a 6DoF rigid-body transformation (rotation and translation) is insufficient to align the two point clouds, this method might be a suitable alternative.

Examples

The following shows the non-rigid registration of two mobile mapping LiDAR point clouds in an urban environment:

Non-rigid registration of two mobile mapping LiDAR point clouds (city) (The effect of registration can best be seen on the overhead lines)

The method is quite flexible. In this example, it was used to estimate a tree’s motion field between sunset (red) and sunrise (green):

Non-rigid registration of two terrestrial LiDAR point clouds of a tree

Another example is the non-rigid registration of two mobile mapping LiDAR point clouds of a railway track (full video here):

Non-rigid registration of two mobile mapping LiDAR point clouds (rail)

Paper

The paper can be found here - it can be cited as:

@article{glira2023a, article-number = {5348}, author = {Glira, Philipp and Weidinger, Christoph and Otepka-Schremmer, Johannes and Ressl, Camillo and Pfeifer, Norbert and Haberler-Weber, Michaela}, doi = {10.3390/rs15225348}, issn = {2072-4292}, journal = {Remote Sensing}, number = {22}, title = {Nonrigid Point Cloud Registration Using Piecewise Tricubic Polynomials as Transformation Model}, url = {https://www.mdpi.com/2072-4292/15/22/5348}, volume = {15}, year = {2023} }

2D Prototype

A prototype implementation of this algorithm for 2D point clouds written in Matlab can be found here.

Building

A predefined development environment for VSCode is provided here. To use this environment, simply open this repository in VSCode and: 1. Open the devcontainer with the command Dev Containers: Reopen in Container. This will automatically build the development environment and open it. Then run in the container: 1. The command CMake: Select a Kit to select a compiler. 2. The command CMake: Select Variant to select a the Release build type. 3. The command CMake: Build to build all targets. 4. The command CMake: Run tests to run the tests. 2. You can find the two executables in the bin directory: - nonrigid-icp is used to estimate the non-rigid transformation between two point clouds. - nonrigid-icp-transform is used to apply the estimated transformation to a point cloud.

Star History

Star History Chart``

Owner

  • Name: AIT - Assistive & Autonomous Systems
  • Login: AIT-Assistive-Autonomous-Systems
  • Kind: organization
  • Location: Austria

GitHub Events

Total
  • Issues event: 4
  • Watch event: 7
  • Delete event: 1
  • Issue comment event: 1
  • Push event: 12
  • Pull request review event: 1
  • Pull request event: 2
  • Fork event: 1
  • Create event: 2
Last Year
  • Issues event: 4
  • Watch event: 7
  • Delete event: 1
  • Issue comment event: 1
  • Push event: 12
  • Pull request review event: 1
  • Pull request event: 2
  • Fork event: 1
  • Create event: 2

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 2
  • Total pull requests: 0
  • Average time to close issues: almost 2 years
  • Average time to close pull requests: N/A
  • Total issue authors: 2
  • Total pull request authors: 0
  • Average comments per issue: 0.5
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • weidinger-c (2)
  • pglira (1)
Pull Request Authors
  • weidinger-c (1)
Top Labels
Issue Labels
Pull Request Labels

Dependencies

.devcontainer/Dockerfile docker
  • mcr.microsoft.com/devcontainers/cpp 1-ubuntu-22.04 build