Translator Disclaimer
Presentation + Paper
12 April 2021 Dynamic fire and smoke detection and classification for flashover prediction
Author Affiliations +
Flashover is a dangerous phenomenon caused by near-simultaneous ignition of exposed materials. It is one of the major causes of firefighter fatalities. Research has been done using CMOS vision cameras combined with thermal sensors to perform remote detection and dynamic classification of fire and smoke patterns. Tests and experiments have been done to detect fire and smoke remotely. The inexpensive visible and infrared sensors used in the tests corroborate and closely follow the detailed trends recorded by the more expensive (and less mobile) radiometers and thermocouples. Deep neural networks (DNN) have been used to detect, classify and track fire and smoke areas. Real-time segmentation is utilized to measure the fire and smoke boundaries. The segmentations are used to dynamically monitor fluctuations in temperature, fire size and smoke progression in the monitored areas. A fire and smoke progression curve has been drawn to predict the flashover point. In the paper, data analysis and preliminary results will be shown.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Alexander Huyen, Kyongsik Yun, Sky De Baun, Samuel Wiggins, Jessi Bustos, Thomas Lu, and Edward Chow "Dynamic fire and smoke detection and classification for flashover prediction", Proc. SPIE 11735, Pattern Recognition and Tracking XXXII, 1173502 (12 April 2021);

Flame detectors

Infrared sensors


CMOS sensors

Data analysis

Image classification

Neural networks


Evaluating uniformity of IR reference sources
Proceedings of SPIE (October 13 2015)
UAVs for wildland fires
Proceedings of SPIE (May 03 2018)
Commercial fusion camera
Proceedings of SPIE (April 18 2006)

Back to Top