Detail výsledku
Fire Segmentation in Still Images
Koplík Karel, Ing.
Hradiš Michal, Ing., Ph.D., UAMT (FEKT), UPGM (FIT)
Zemčík Pavel, prof. Dr. Ing., dr. h. c., UAMT (FEKT), UPGM (FIT)
In this paper, we propose a novel approach to fire localization in images based on a state of the art semantic segmentation method DeepLabV3. We compiled a data set of 1775 images containing fire from various sources for which we created polygon annotations. The data set is augmented with hard non-fire images from SUN397 data set. The segmentation method trained on our data set achieved results better than state of the art results on BowFire data set. We believe the created data set will facilitate further development of fire detection and segmentation methods, and that the methods should be based on general purpose segmentation networks.
Fire detection, Semantic segmentation, Deep learning, Neural Networks, Emergency situation analysis
@inproceedings{BUT162094,
author="Jozef {Mlích} and Karel {Koplík} and Michal {Hradiš} and Pavel {Zemčík}",
title="Fire Segmentation in Still Images",
booktitle="Springer International Publishing",
year="2020",
series="Lecture Notes in Computer Science",
pages="27--37",
publisher="Springer International Publishing",
address="Auckland",
doi="10.1007/978-3-030-40605-9\{_}3",
isbn="978-3-030-40605-9",
url="https://link.springer.com/chapter/10.1007%2F978-3-030-40605-9_3"
}Moderní metody zpracování, analýzy a zobrazování multimediálních a 3D dat, VUT, Vnitřní projekty VUT, FIT-S-20-6460, zahájení: 2020-03-01, ukončení: 2023-02-28, ukončen
Zpracování, zobrazování a analýza multimediálních a 3D dat, VUT, Vnitřní projekty VUT, FIT-S-17-3984, zahájení: 2017-03-01, ukončení: 2020-02-29, ukončen