Skip to content

UI for processing of data collected with VelodyneHDL lidar

License

Notifications You must be signed in to change notification settings

walzimmer/pylidartracker

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

39 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PyLidarTracker

PyLidarTracker is a desktop traffic analysis software for pre-processing point cloud videos captured by a static VelodyneHDL LiDAR (so far only HDL32). Pre-processed clouds can be clustered into road users whose tracks that can be exported for fruther analysis. The software is developed at Aalborg University Denmark, Traffic Research Group.

GitHub PyPI

Features

  • Open UDP Network stream .pcap files captured by Velodyne for preview.
  • pre-processing/editing in terms of coordinate transformation, clipping, background subtraction, clustering and cluster tracking.
  • Save project configuration files that can be appled to the files from similar experimental setup to improve reproducibility and avoid repetitive steps in the analysis proccess.
  • Output .json file with detected road user ID, time and position per point cloud video frame.

Preview

Getting started

Installation from source

Latest version of pylidartracker can be installed from source by cloning this repo and using given setup.py. A virtual environment like virtualenv or conda is recommended to avoid dependency problems. Example with conda:

# create environment
conda create -n pylidar python=3.8

# clone source code and change directory to it
git clone https://github.com/mihsamusev/pylidartracker.git
cd pylidartracker

# looks for setup.py to install into the environment
pip install -e .

Run the application using pylidartracker command, which is a shourtcut for python src/app.py.

Example files

The files for the demo are store in this zip. The folder contains short point cloud videos street.pcap and office.pcap as well as optional project configuration files street_config.json and office_config.json.

Typical workflow:

  1. Download the .zip folder with the example files.
  2. Open a .pcap file to be analyzed, choose amount of frames to preview. Small amount of frames (100-300) is suggested because it allows to quickly define and save configuration describin processing steps that are later going to be applied for the entire file.
  3. Perform pre-processing, coordinate transformation, cloud clipping and background subtraction to prepare the point cloud frames for clustering.
  4. Perform clustering of point cloud frames into individual objects.
  5. Perform cluster tracking.
  6. Optionally, save the previous steps to configuration file that can be re-run later to recreate the processing steps undertaken in the project.
  7. Generate output.

Built with

Frontend:

Backend:

Status

The project is in the process of being refactored as a backend and frontend packages with their own tests. The backend - pylidarlib will allow to perform same point cloud operations in a headless fashion.

Support

Contact msa@build.aau.dk

About

UI for processing of data collected with VelodyneHDL lidar

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%