Wildland Forest Fire Smoke Detection Based on Faster R-CNN using Synthetic Smoke Images

In this paper, Faster R-CNN was used to detect wildland forest fire smoke to avoid the complex manually feature extraction process in traditional video smoke detection methods. Synthetic smoke images are produced by inserting real smoke or simulative smoke into forest background to solve the lack of...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Procedia engineering Ročník 211; s. 441 - 446
Hlavní autoři:	Zhang, Qi-xing, Lin, Gao-hua, Zhang, Yong-ming, Xu, Gao, Wang, Jin-jun
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 2018
Témata:	deep learning faster R-CNN synthetic smoke image video smoke detection wildland forest fire smoke faster R-CNN deep learning synthetic smoke image wildland forest fire smoke video smoke detection
ISSN:	1877-7058, 1877-7058
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	In this paper, Faster R-CNN was used to detect wildland forest fire smoke to avoid the complex manually feature extraction process in traditional video smoke detection methods. Synthetic smoke images are produced by inserting real smoke or simulative smoke into forest background to solve the lack of training data. The models trained by the two kinds of synthetic images respectively are tested in dataset consisting of real fire smoke images. The results show that simulative smoke is the better choice and the model is insensitive to thin smoke. It may be possible to further boost the performance by improving the synthetic process of forest fire smoke images or extending this solution to video sequences.
ISSN:	1877-7058 1877-7058
DOI:	10.1016/j.proeng.2017.12.034