| Abstract | Flashover phenomena accompanying rapid fire propagation in a room occur when the hot smoke from a fire accumulates in the room's upper part. This phenomenon presents one of the most frightening and challenging situations for firefighters. A typical approach to mitigate and prevent the impact of flashover is to train firefighters to monitor a few common indicators of fire in pre-flashover time, such as moving dark smoke, high heat, and fire rollover. In actual compartment fire events, these pre-flashover indicators are hard to recognize. Furthermore, determination of exact flashover time is difficult by just observing fire activities while there are other vital rescue duties to do by firefighters. Hence, automatic detection and prediction of flashover in real time are of paramount importance to save lives and reduce the cost of damages. Flashover prediction is still an open area of research by fire safety experts. Deep convolutional neural networks are currently dominating the area of computer vision, and these state-of-the-art deep learning models have been successfully used in various applications, including object detection, localization, and segmentation. Unlike previous studies that use RGB images, sensors, and gauges, we utilized the power of deep learning techniques to detect flashover from image sequences captured by thermal infrared (IR) cameras. Our experimental results indicate that not only our proposed approach can detect flashover in IR video data with high precision, but it can detect flashover a few frames before happening. Our technique is a promising approach that can be used in future for flashover prediction in real time. |
|---|
