Design of Machine Learning-Based Smoke Surveillance

被引:1
作者
Ho, Chao-Ching [1 ]
机构
[1] Natl Yunlin Univ Sci & Technol, Dept Mech Engn, Yunlin 64002, Taiwan
关键词
Surveillance System; Support Vector Machine; Fire Smoke Detection; Motion Segmentation;
D O I
10.1166/asl.2011.1441
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
A real-time machine learning-based fire smoke detection method that can be incorporated with a automatic monitoring system for early alerts is proposed by this paper. The successive processing steps of our real-time algorithm are using the motion segmentation algorithm to register the possible smoke position in a video and then analyze the spectral, spatial and motion orientation characteristics of the smoke regions in the image sequences. Characterization of smoke was carried out by calculating arithmetic mean and standard deviation from the extracted feature vectors, and the non-linear classification method using support vector machine is applied to give the potential fire smoke candidate region. Then, the continuously adaptive mean shift (CAMSHIFT) vision tracking algorithm is employed to provide feedback of the fire smoke real-time position at a high frame rate. Experimental results in a variety of conditions show the proposed support vector machine-based fire smoke detection method is capable of detecting fire smoke reliably and robustly.
引用
收藏
页码:2272 / 2275
页数:4
相关论文
共 9 条
[1]  
[Anonymous], 2006, BUILD ENVIRON, DOI DOI 10.1016/j.buildenv.2005.05.036
[2]  
[Anonymous], ADVANTAGE FOREST ENG
[3]  
Chen T. H., 2006, P INT INF HID MULT S
[4]  
Ho C.-C., 2009, P IEEE ASME ADV INT
[5]   Machine vision-based real-time early flame and smoke detection [J].
Ho, Chao-Ching .
MEASUREMENT SCIENCE AND TECHNOLOGY, 2009, 20 (04)
[6]  
Lai C. L., 2007, P INSTR MEAS TECHN W
[7]  
Toreyin B. Ugur, 2006, 2006 14th European Signal Processing Conference. Proceedings
[8]  
Toreyin B.U., 2005, 2005 13 EUR SIGN PRO, P1
[9]  
Xiong Z, 2007, P SUPPR DET RES APPL