000			01324nab a2200205 4500
005			20260520000945.0
008			260224s2010 xxu
245	0	0	_aVideo fire smoke detection using motion and color features
260			_a _b _cjul. 2010
270			_a26/08/2010 ; 26/08/2010
300			_a13 p. ; 651-663
520			_aTranscripción del resumen del autor. A novel video smoke detection method using both color and motion features is presented. The result of optical flow is assumed to be an approximation of motion field. Background estimation and color-based decision rule are used to determine candidate smoke regions. The Lucas Kanade optical flow algorithm is proposed to calculate the optical flow of candidate regions. And the motion features are calculated from the optical flow results and use to differentiate smoke from some other moving objects. Finally, a back-propagation neural network is used to classify the smoke features from non-fire smoke features. Experiments show that the algorithm is significant for improving the accuracy of video smoke detection and reducing false alarms.
581			_a3
773	0		_tFire Technology _g46
942			_cARTICULO
100	1		_aChunyu, Yu _946636
100	1		_aJun, Fang _946637
100	1		_aJinjun, Wang _946638
999			_c176323 _d176323