| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 734574 | Optics & Laser Technology | 2013 | 9 Pages |
To improve the video fire detection rate, a robust fire detection algorithm based on the color, motion and pattern characteristics of fire targets was proposed, which proved a satisfactory fire detection rate for different fire scenes. In this fire detection algorithm: (a) a rule-based generic color model was developed based on analysis on a large quantity of flame pixels; (b) from the traditional GICA (Geometrical Independent Component Analysis) model, a Cumulative Geometrical Independent Component Analysis (C-GICA) model was developed for motion detection without static background and (c) a BP neural network fire recognition model based on multi-features of the fire pattern was developed. Fire detection tests on benchmark fire video clips of different scenes have shown the robustness, accuracy and fast-response of the algorithm.
► Proposed a robust fire detection algorithm based on the color, motion and pattern characteristics of fire targets. ► Developed a rule-based generic color model. ► Developed a Cumulative Geometrical Independent Component Analysis (C-GICA) model for motion detection. ► Developed a BP neural network fire recognition model based on the multi-features of the fire pattern.
