EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Cross domain additive manufacturing video object segmentation dataset

Calvin Wetzel, Hector Santos-Villalobos, James Haley, Vladimir Orlyanchik, Mario Rodriguez Parra, Mithulan Paramanathan, Tom Feldhausen, Michael Sebok, Chris Masuo, Vincent Paquit

Data in Brief · 2026-08 · 69 · 113249

DOI: 10.1016/j.dib.2026.113249 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data in Brief, 2026-08. Verfasst von Calvin Wetzel und 9 weiteren Autor:innen. Beteiligte Einrichtung: The University of Tennessee, 1520 Middle Drive, Knoxville, 37996-2250, TN, United States. Die Arbeit nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Office of Critical Minerals and Energy Innovation, Advanced Materials and Manufacturing Technologies Office, US Department of Energy.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article presents labeled data collected from video footage of additive manufacturing processes. This computer vision dataset contains 90 labeled additive manufacturing video segments across four distinct additive manufacturing processes, amounting to 900 labeled, object instance video frames. The technologies covered by the dataset include laser hot-wire additive manufacturing (LHW-DED), plasma arc welding (PAW), tungsten inert gas wire arc additive manufacturing (TIG-WAAM), and polymer-based additive manufacturing (visPolymer and irPolymer). For each of the manufacturing processes, build deposition video was captured and then randomly sampled into 10 frame-long video segments. Depending on the manufacturing process, two of the following four object instance classes are labeled in each frame: Melt Pool, Feed Wire, Nozzle, and Material. Since the dataset's directory organization follows that of common video object segmentation (VOS) datasets, such as coMplex video Object SEgmentation (MOSE), MOSEv2, Densely Annotated Video Segmentation (DAVIS), and YouTube-VOS, it can be easily integrated into other VOS model training pipelines for foundation model fine-tuning, training, or inference capability testing. This dataset provides researchers access to labeled additive manufacturing object instances for VOS tasks.

Schlagwörter

Stichwörter der Autor:innen

Computer visionDomain adaptationFine-tuningFoundation modelsLoRASAM 2VOS

Autor:innen und Institutionen

  • The University of Tennessee, 1520 Middle Drive, Knoxville, 37996-2250, TN, United States.
  • Oak Ridge National Laboratory, 1 Bethel Valley Rd, Oak Ridge, 37830, TN, United States.

Förderung

  • Office of Critical Minerals and Energy Innovation
  • Advanced Materials and Manufacturing Technologies Office
  • US Department of Energy

Zitieren

APA

Wetzel, C., Santos-Villalobos, H., Haley, J., Orlyanchik, V., Parra, M. R., Paramanathan, M., Feldhausen, T., Sebok, M., Masuo, C., & Paquit, V. (2026). Cross domain additive manufacturing video object segmentation dataset. Data in Brief, 69, 113249. https://doi.org/10.1016/j.dib.2026.113249

Vancouver

Wetzel C, Santos-Villalobos H, Haley J, Orlyanchik V, Parra MR, Paramanathan M, et al. Cross domain additive manufacturing video object segmentation dataset. Data in Brief. 2026;69:113249. doi:10.1016/j.dib.2026.113249

BibTeX
@article{Wetzel2026,
  author = {Wetzel, Calvin and Santos-Villalobos, Hector and Haley, James and Orlyanchik, Vladimir and Parra, Mario Rodriguez and Paramanathan, Mithulan and Feldhausen, Tom and Sebok, Michael and Masuo, Chris and Paquit, Vincent},
  title = {Cross domain additive manufacturing video object segmentation dataset},
  journal = {Data in Brief},
  year = {2026},
  volume = {69},
  pages = {113249},
  doi = {10.1016/j.dib.2026.113249}
}
Kostenlos starten →