This dataset contains a curated database of OH structures extracted from OH-PLIF measurements. The database is utilised for the generation of synthetic, automatically annotated training data via physics-informed domain randomisation. The resulting synthetic dataset is subsequently used for training of DL-based semantic segmentation models for transferable OH-LIF flame detection.
For further details and citation, please refer to the submitted paper:
B. Jose, D. Greenblatt, R. P. Lindstedt, A. Breicher, D. Geyer, O. Lammel, F. Hampp, Transferable DL for in-situ validated LIF segmentation, submitted to the Proceedings of the Combustion Institute (2026)
Data Samples: