Computer Vision Based Fire Detection

In this paper we use a combination of techniques to detect fire in video data. First, the algorithm locates regions of the video where there is movement. From these regions firecolored pixels are extracted using a perceptron. Lastly, we use dynamic texture analysis to confirm that these moving, fire-colored regions have the temporal and motion characteristics of fire.

[1]  B. De Moor,et al.  Subspace angles between linear stochastic models , 2000, CDC 2000.

[2]  Richard J. Martin.  A metric for ARMA processes , 2000, IEEE Trans. Signal Process..

[3]  A. Enis Çetin,et al.  Contour based smoke detection in video using wavelets , 2006, 2006 14th European Signal Processing Conference.

[4]  Nuno Vasconcelos,et al.  Classifying Video with Kernel Dynamic Textures , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Stefano Soatto,et al.  Dynamic Textures , 2003, International Journal of Computer Vision.

[6]  Wen-Bing Horng,et al.  Image-Based Fire Detection Using Neural Networks , 2006, JCIS.

[7]  Payam Saisan,et al.  Dynamic texture recognition , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[8]  Y.H. Chen,et al.  A Real Time Video Processing Based Surveillance System for Early Fire and Flood Detection , 2007, 2007 IEEE Instrumentation & Measurement Technology Conference IMTC 2007.

[9]  Mubarak Shah,et al.  Flame recognition in video , 2000, Proceedings Fifth IEEE Workshop on Applications of Computer Vision.

[10]  A. Enis Çetin,et al.  Computer vision based method for real-time fire and flame detection , 2006, Pattern Recognit. Lett..

[11]  Daniel Cremers,et al.  Dynamic texture segmentation , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[12]  Xiaojun Qi,et al.  A computer vision-based method for fire detection in color videos , 2009 .