GitHub Repo GitHub Docs pypi package Downloads tutorial

Documentation

arcjetCV Logo

arcjetCV

Package to process arcjet videos and segment the edge of the shock and of the sample.

arcjetCV Functionality

Installation

PyPi Installation (Universal)

Prerequisites:

  • Ensure you have Python 3.8 or higher installed.

To install arcjetCV via pip from PyPi, run:

pip install arcjetCV

This will install arcjetCV along with its dependencies.

Note for macOS Users:

You might need to install Xcode Command Line Tools:

xcode-select --install

Note for Linux Users:

You may need to install libxcb-cursor. Use your package manager to install it:

For Ubuntu/Debian-based distributions:

sudo apt-get install libxcb-cursor0

For Fedora:

sudo dnf install libxcb-cursor

For Arch Linux:

sudo pacman -S libxcb

Developer Installation

Prerequisites:

  • A valid git installation.

  • Miniconda or Anaconda for environment and package management:

  • For macOS users, make sure the Xcode Command Line Tools are installed:

xcode-select --install

To install arcjetCV for development, follow these steps:

  1. Install git-lfs:

    Download and install it from here.

  2. Clone the repository and install the package:

git clone https://github.com/magnus-haw/arcjetCV.git
cd arcjetCV

# CPU environment (recommended default)
conda env create -f env/arcjetCV_env_cpu.yml

# GPU environment (NVIDIA GPU + CUDA required)
# conda env create -f env/arcjetCV_env_gpu.yml

conda activate arcjetcv
python -m pip install -e .

The -e flag stands for ‘editable’ and means that any changes to the local source code will immediately affect the arcjetCV package and GUI.

Choose the environment file based on your hardware:

  • env/arcjetCV_env_cpu.yml: works on any machine (recommended default).

  • env/arcjetCV_env_gpu.yml: use this only when you have a compatible NVIDIA GPU and drivers/CUDA stack configured.

How to Run

PyPI Users

Launch the GUI:

arcjetcv

Developer Users

Activate your conda environment first:

conda activate arcjetcv

Then launch the GUI:

arcjetcv

Or use arcjetCV’s Python API inside a Python script, e.g., test.py:

import arcjetCV as arcv
video = arcv.Video("tests/arcjet_test.mp4")

Run the script with:

python test.py

Citing

If you use arcjetCV in your research, please use the following BibTeX entry to cite our paper:

@article{doi:10.2514/1.A36132,
author = {Quintart, Alexandre M. and Haw, Magnus A. and Semeraro, Federico},
title = {arcjetCV: Open-Source Software to Analyze Material Ablation},
journal = {Journal of Spacecraft and Rockets},
volume = {62},
number = {5},
pages = {1644-1653},
year = {2025},
doi = {10.2514/1.A36132},
URL = {https://doi.org/10.2514/1.A36132},
eprint = {https://doi.org/10.2514/1.A36132},
abstract = { ArcjetCV is an open-source Python software designed to automate time-resolved measurements of heat shield material ablation and recession rates from arcjet test video footage. This new automated and accessible capability enables two-dimensional in situ recession characterization from profile video. ArcjetCV automates the video segmentation process using two primary machine-learning models: a one-dimensional (1D) Convolutional Neural Network (CNN) to infer the time window of interest and a two-dimensional CNN for image segmentation. A graphical user interface simplifies the user experience and an application programming interface allows users to call the core functions from scripts, enabling batch video processing. ArcjetCV’s capability to measure time-resolved recession the enables characterization of nonlinear processes (nonlinear recession, shrinkage, swelling, etc.), contributing to higher-fidelity validation and improved modeling of heat shield material performance. The source code associated with this paper can be found at https://github.com/magnus-haw/arcjetCV. }}