Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

arcjetCV: an open-source software to analyze material ablation

Alexandre Quintart, Magnus Haw, Federico Semeraro

TL;DR

arcjetCV presents an open-source, Python-based tool for automating time-resolved analysis of arcjet test videos, focusing on material recession, edge segmentation, and shock standoff. It combines a 1D CNN for time segmentation, a 2D UNet with an Xception encoder for edge/feature segmentation, and Local Outlier Factor for frame quality control, all accessible via a GUI and a Python API for batch processing. The methodology includes synthetic data-based training, SAM+GrabCut-driven dataset construction, and demonstrates capabilities in non-linear recession, shape change, and CFD-aligned shock validation. This work significantly improves fidelity and efficiency of TPS material validation and modeling, and is already leveraged at NASA arcjet facilities, with ongoing plans for handling noisier videos and 3D surface reconstruction.

Abstract

arcjetCV is an open-source Python software designed to automate time-resolved measurements of heatshield material recession and recession rates from arcjet test video footage. This new automated and accessible capability greatly exceeds previous manual extraction methods, enabling rapid and detailed characterization of material recession for any sample with a profile video. arcjetCV automates the video segmentation process using machine learning models, including a one-dimensional (1D) Convolutional Neural Network (CNN) to infer the time-window of interest, a two-dimensional (2D) CNN for image and edge segmentation, and a Local Outlier Factor (LOF) for outlier filtering. A graphical user interface (GUI) simplifies the user experience and an application programming interface (API) allows users to call the core functions from scripts, enabling video batch processing. arcjetCV's capability to measure time-resolved recession in turn enables characterization of non-linear processes (shrinkage, swelling, melt flows, etc.), contributing to higher fidelity validation and improved modeling of heatshield material performance. The source code associated with this article can be found at https://github.com/magnus-haw/arcjetCV.

arcjetCV: an open-source software to analyze material ablation

TL;DR

arcjetCV presents an open-source, Python-based tool for automating time-resolved analysis of arcjet test videos, focusing on material recession, edge segmentation, and shock standoff. It combines a 1D CNN for time segmentation, a 2D UNet with an Xception encoder for edge/feature segmentation, and Local Outlier Factor for frame quality control, all accessible via a GUI and a Python API for batch processing. The methodology includes synthetic data-based training, SAM+GrabCut-driven dataset construction, and demonstrates capabilities in non-linear recession, shape change, and CFD-aligned shock validation. This work significantly improves fidelity and efficiency of TPS material validation and modeling, and is already leveraged at NASA arcjet facilities, with ongoing plans for handling noisier videos and 3D surface reconstruction.

Abstract

arcjetCV is an open-source Python software designed to automate time-resolved measurements of heatshield material recession and recession rates from arcjet test video footage. This new automated and accessible capability greatly exceeds previous manual extraction methods, enabling rapid and detailed characterization of material recession for any sample with a profile video. arcjetCV automates the video segmentation process using machine learning models, including a one-dimensional (1D) Convolutional Neural Network (CNN) to infer the time-window of interest, a two-dimensional (2D) CNN for image and edge segmentation, and a Local Outlier Factor (LOF) for outlier filtering. A graphical user interface (GUI) simplifies the user experience and an application programming interface (API) allows users to call the core functions from scripts, enabling video batch processing. arcjetCV's capability to measure time-resolved recession in turn enables characterization of non-linear processes (shrinkage, swelling, melt flows, etc.), contributing to higher fidelity validation and improved modeling of heatshield material performance. The source code associated with this article can be found at https://github.com/magnus-haw/arcjetCV.
Paper Structure (25 sections, 9 figures, 2 tables)

This paper contains 25 sections, 9 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Software Architecture
  3. Graphical User Interface
  4. Video Processing
  5. Data Analysis
  6. Python API
  7. Video Class
  8. VideoMeta Class
  9. ArcjetProcessor Class
  10. Methodology
  11. Time Segmentation
  12. Architecture
  13. Dataset Generation
  14. Training and Results
  15. Local Outlier Factor
  16. ...and 10 more sections

Figures (9)

  • Figure 1: GUI Video Processing window
  • Figure 2: GUI Data Analysis window
  • Figure 3: Normalized time series derived from the brightness intensity of video frames
  • Figure 4: 1D CNN model training
  • Figure 5: Metrics for the Xception model trained up to 40 epochs
  • ...and 4 more figures