Abstract
This paper proposes a flame detection framework based on the color, dynamics, and flickering properties of flames. The distribution of flame colors is modeled by a Gaussian mixture model whose number of Gaussian components is estimated by a Dirichlet process from training data rather than set empirically. The proposed approach estimates the flame color distribution more accurately as it can determine the number of Gaussian components of the mixture model automatically. Additionally, a probabilistic saliency analysis method and a one-dimensional wavelet transform are used to extract motion saliency and filtered temporal series as features, describing the dynamics and flickering properties of flames. The developed Dirichlet process Gaussian mixture model based approach for autonomous flame detection is tested on various videos and achieves framewise accuracy higher than 95%.
| Original language | English |
|---|---|
| Pages (from-to) | 1146-1154 |
| Number of pages | 9 |
| Journal | IEEE Transactions on Industrial Informatics |
| Volume | 14 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - 1 Nov 2017 |
Funding
Manuscript received March 30, 2017; revised August 15, 2017 and September 6, 2017; accepted October 6, 2017. Date of publication November 1, 2017; date of current version March 1, 2018. This work was supported in part by the China Scholarship Council and in part by the EC Seventh Framework Programme [FP7 2013–2017] TRAcking in compleX sensor systems Grant Agreement 607400. Paper no. TII-17-0609. (Corresponding author: Zhenglin Li.) Z. Li and L. S. Mihaylova are with the Department of Automatic Control and Systems Engineering, University of Sheffield, Sheffield S1 3JD, U.K. (e-mail: [email protected]; L.S.Mihaylova@ sheffield.ac.uk).
Keywords
- Dirichlet process Gaussian mixture model (DPGMM)
- flame detection
- saliency analysis