1,720,968 research outputs found
Code for using and training spray segmentation models
No full textThis dataset contains the necessary code for using our spray segmentation model used in the paper, ML-based semantic segmentation for quantitative spray atomization description. See README for more information
QoI - Droplets
No full text
This dataset consists of a database of regular and distorted droplets with droplet clusters extracted from high-resolution shadowgraphy images in technical sprays. It serves as a subclass for generating synthetic training data via domain randomisation, which is subsequently used to train Deep Learning (DL) based image segmentation models.
A more detailed description is provided in the corresponding paper:
https://doi.org/10.1016/j.ijmultiphaseflow.2023.104702
Data Samples
Regular droplets:
Distorted droplets:
</p
Nuisance - OOFObjs
No full text
This dataset contains the database of Out Of Focus Objects (OOFObjs)—currently mostly droplets and used for droplet sizing in shadowgraphy analysed sprays.
The database is one subclass utilised in the generation of synthetic training dataset via domain randomisation. The resulting dataset is subsequently used for training of DL-based image segmentation models.
A more detailed description is provided in the corresponding paper:
https://doi.org/10.1016/j.ijmultiphaseflow.2023.104702
Data Samples:
</p
Code for training and using the soot (instance) segmentation models
No full textThis dataset contains the necessary code for using our soot (instance) segmentation model used for segmenting soot filaments from PIV (Mie scattering) images. In the corresponding paper, an ablation study is conducted to delineate the effects of domain randomisation parameters of synthetically generated training data on the segmentation accuracy. The best model is used to extract high-level statistics from soot filaments in an RQL-type model combustor to enhance the fundamental understanding soot formation, transport and oxidation. B. Jose, K. P. Geigle, F. Hampp, Domain-Randomised Instance-Segmentation Benchmark for Soot in PIV Images, submitted to Machine Learning: Science and Technology (2025
QoI - Tracer particles
No full text
This dataset contains the database of image snippets of dense clusters of PIV tracer particles (i.e. Mie scattering) marking the reactants within sooting flame measurements in an RQL-type combustor.
The database is one subclass utilised in the generation of synthetic training data via domain randomisation. The resulting dataset is subsequently used for training of DL-based image segmentation models.
For further details and citation, please refer to the submitted paper:
B. Jose, K. P. Geigle, F. Hampp, Domain-Randomised Instance-Segmentation Benchmark for Soot in PIV Images, submitted to Machine Learning: Science and Technology (2025)
Data Samples:
</p
Background - Tracer particle regions
No full text
This dataset contains the database of image snippets of PIV tracer particles (i.e. Mie scattering) in the background, extracted from sooting flame measurements within an RQL-type combustor.
The database is one subclass utilised in the generation of synthetic training data via domain randomisation. The resulting dataset is subsequently used for training of DL-based image segmentation models.
For further details and citation, please refer to the submitted paper:
B. Jose, K. P. Geigle, F. Hampp, Domain-Randomised Instance-Segmentation Benchmark for Soot in PIV Images, submitted to Machine Learning: Science and Technology (2025)
Data Samples:
</p
Nuisance - OOPObjs
No full text
This dataset contains the database of Out Of Plane Objects (OOPObjs) extracted from PIV (Mie scattering) measurements within an RQL-type combustor.
The database is one subclass utilised in the generation of synthetic training data via domain randomisation. The resulting dataset is subsequently used for training of DL-based image segmentation models.
For further details and citation, please refer to the submitted paper:
B. Jose, K. P. Geigle, F. Hampp, Domain-Randomised Instance-Segmentation Benchmark for Soot in PIV Images, submitted to Machine Learning: Science and Technology (2025)
Data Samples:
</p
QoI - Soot filaments
No full text
This dataset contains the database of soot filaments extracted from PIV (Mie scattering) measurements, CFD simulations and generative models.
The database is one subclass utilised in the generation of synthetic training data via domain randomisation. The resulting dataset is subsequently used for training of DL-based image segmentation models.
For further details and citation, please refer to the submitted paper:
B. Jose, K. P. Geigle, F. Hampp, Domain-Randomised Instance-Segmentation Benchmark for Soot in PIV Images, submitted to Machine Learning: Science and Technology (2025)
Data Samples:
Real soot:
Soot from generative models:
Soot from simulations:
</p
Jose et al. MLST 2025 - Code, Data and Models
No full textThis dataset hosts the code, data and models needed for replication of the work mentioned in Jose et al. MLST 2025. In the paper, an ablation study is conducted to delineate the effects of domain randomisation parameters of synthetically generated training data on the segmentation accuracy. The best model is used to extract high-level statistics from soot filaments in an RQL-type model combustor to enhance the fundamental understanding soot formation, transport and oxidation. B. Jose, K. P. Geigle, F. Hampp, Domain-Randomised Instance-Segmentation Benchmark for Soot in PIV Images, submitted to Machine Learning: Science and Technology (2025
- …
