Estimation of 3D shape and volume of fire plumes from multiple views

J. A. Blanco; M. Pardas; J. R. Casas; R. Paugam; A. Agueda; J. Wagner; Russell A. Parsons; E. Planas

doi:10.1088/1742-6596/2885/1/012075

Treesearch

Estimation of 3D shape and volume of fire plumes from multiple views

Formally Refereed

Authors:

J. A. Blanco, M. Pardas, J. R. Casas, R. Paugam, A. Agueda, J. Wagner, Russell A. Parsons, E. Planas

Year:

2024

Type:

Scientific Journal

Station:

Rocky Mountain Research Station

DOI:

https://doi.org/10.1088/1742-6596/2885/1/012075

Source:

Journal of Physics: Conference Series. 2885: 012075.

Download (PDF 1.26 MB)

Download (PDF 1.26 MB): https://research.fs.usda.gov/download/treesearch/68882.pdf

Abstract

This study evaluates deep-learning and Shape from Silhouette (SfS) methods for 3D reconstruction of smoke plumes. It demonstrates the deep-learning method's superiority in cases with limited camera views and calibration data, achieving high-quality reconstructions of semitransparent smoke without precise calibration. The research emphasizes the significance of preprocessing and data appearance for neural network efficacy. By improving 3D reconstruction techniques, this work aids in advancing wildfire tracking and environmental analysis, offering a practical approach for real-world applications in fire science.

Keywords

Shape from Silhouette (SfS) methods, 3D reconstruction, smoke plumes

Citation

Blanco, J. A.; Pardas, M.; Casas, J. R.; Paugam, R.; Agueda, A.; Wagner, J.; Parsons, R. A.; Planas, E. 2024. Estimation of 3D shape and volume of fire plumes from multiple views. Journal of Physics: Conference Series. 2885: 012075.