Wildland Forest Fire Smoke Detection Based on Faster R-CNN using Synthetic Smoke Images
Autor: | Lin Gaohua, Jinjun Wang, Yongming Zhang, Qixing Zhang, Gao Xu |
---|---|
Rok vydání: | 2018 |
Předmět: |
Smoke
Training set business.industry Computer science Feature extraction ComputingMilieux_PERSONALCOMPUTING ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Process (computing) 020101 civil engineering Video sequence 02 engineering and technology General Medicine GeneralLiterature_MISCELLANEOUS Fire smoke 0201 civil engineering 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence business ComputingMethodologies_COMPUTERGRAPHICS |
Zdroj: | Procedia Engineering. 211:441-446 |
ISSN: | 1877-7058 |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |