Image-Based Fire Detection Using Neural Networks
Wen-Bing Horng 0, Jian-Wen Peng
Available Online October 2006.
- https://doi.org/10.2991/jcis.2006.301How to use a DOI?
- burning degree estimation, color masking, fire flame detection, neural network
- An image-based fire detection method using neural networks is proposed in this paper. First, flame color features, based on the HSI color model, are trained by a backpropagation neural network for flame recognition. Then, based on the learned flame color features, regions with fire-like colors are roughly separated from an image. Besides segmenting flame regions, background objects with similar fire colors or resulted from the reflection of fire flames are also separated from the image. In order to get rid of these spurious fire-like regions, the image difference method and the invented color masking technique are applied. Finally, a compact method is devised to estimate the burning degree of fire flames so that users could be informed with a proper warning alarm. The proposed system can achieve 96.47% fire detection rate on average.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Wen-Bing Horng AU - Jian-Wen Peng PY - 2006/10 DA - 2006/10 TI - Image-Based Fire Detection Using Neural Networks BT - 9th Joint International Conference on Information Sciences (JCIS-06) PB - Atlantis Press SN - 1951-6851 UR - https://doi.org/10.2991/jcis.2006.301 DO - https://doi.org/10.2991/jcis.2006.301 ID - Horng2006/10 ER -