大空间图像型火焰检测方法研究
|
摘要
为了提高图像型火焰检测算法的准确率,满足其对实时性的要求,采用三帧差分和背景更新相结合的方法,提取运动前景区域。然后在RGB空间和Lab空间建立颜色模型,分割出火焰疑似区域。用Lucas-Kanade稀疏光流算法跟踪运动区域,获取火焰的主运动方向作为火焰识别特征,判断是否是真实的火灾发生。实验结果表明,该算法具有较好的实时性、鲁棒性,能够有效地提高火焰识别的准确率,降低误检率,在大空间公共建筑消防系统中具有重要的应用价值。
In order to improve the accuracy of the image flame detection algorithm and meet its real-time requirement,the three-frame difference and background update combining method is adopted to extract the motion foreground region. The color model is established in the RGB space and Lab space to segment the suspected flame region. The Lucas-Kanade sparse optical flow algorithm is used to track the motion region,and obtain the main motion direction of the flame which is taken as the flame recognition feature to determine whether any real fire occurs. The experimental results show that the algorithm has a good realtime performance and robustness,can effectively improve the accuracy of flame recognition,reduce false detection rate,and has an important application value in the large space public building fire-proof system.
In order to improve the accuracy of the image flame detection algorithm and meet its real-time requirement,the three-frame difference and background update combining method is adopted to extract the motion foreground region. The color model is established in the RGB space and Lab space to segment the suspected flame region. The Lucas-Kanade sparse optical flow algorithm is used to track the motion region,and obtain the main motion direction of the flame which is taken as the flame recognition feature to determine whether any real fire occurs. The experimental results show that the algorithm has a good realtime performance and robustness,can effectively improve the accuracy of flame recognition,reduce false detection rate,and has an important application value in the large space public building fire-proof system.
引文
[1] LI Z,MIHAYLOVA L S,ISUPOVA O,et al. Autonomousflame detection in videos with a Dirichlet process Gaussian mix?ture color model[J]. IEEE transactions on industrial informatics,2018,14(3):1146?1154.
[2] JIANG B,LU Y,LI X,et al. Towards a solid solution of real?time fire and flame detection[J]. Multimedia tools and applica?tions,2015,74(3):689?705.
[3] LI H. Research on a new photoelectric detection method to anti?muzzle′s flame or light disturbance and projectile′s informa?tion recognition in photoelectric detection target[J]. Optoelec?tronics and advanced materials?rapid communications,2014,8(7):653?658.
[4] LI Z,ISUPOVA O,MIHAYLOVA L,et al. Autonomous flamedetection in video based on saliency analysis and optical flow[C]//Proceedings of IEEE International Conference on Multisen?sor Fusion and Integration for Intelligent Systems. Baden?Baden:IEEE,2016:218?223.
[5] DIMITROPOULOS K,BARMPOUTIS P,GRAMMALIDIS N.Spatio?temporal flame modeling and dynamic texture analysisfor automatic video?based fire detection[J]. IEEE transactionson circuits and systems for video technology,2015,25(2):339?351.
[6] TOULOUSE T,ROSSI L,CELIK T,et al. Automatic fire pix?el detection using image processing:a comparative analysis ofrule?based and machine learning?based methods[J]. Signal,im?age and video processing,2016,10(4):647?654.
[7] MAHDIPOUR E, DADKHAH C. Automatic fire detectionbased on soft computing techniques:review from 2000 to 2010[J]. Artificial intelligence review,2014,42(4):895?934.
[8] HAN T,LIN B. Research on flame image recognition methodinnaturalscene[C]//ProceedingsofIEEEInternationalConferenceon Information and Automation. Ningbo:IEEE,2016:1776?1780.
[9] ZHAO X,KONG W,WEI J,et al. Gas chromatography withflame photometric detection of 31 organophosphorus pesticideresidues in Alpinia oxyphylla dried fruits[J]. Food chemistry,2014,162:270?276.
[10]宋宁,强彦,董林佳.林火监测中基于视觉的火焰检测方法[J].科学技术与工程,2017,17(25):268?273.SONG Ning,QIANG Yan,DONG Linjia. Vision based flamedetection method in forest fire monitoring[J]. Science tech?nology and engineering,2017,17(25):268?273.
[11]戴静,严云洋,范勇,等.基于BEMD和SVM的火焰检测算法[J].常州大学学报(自然科学版),2017,29(2):71?77.DAI Jing,YAN Yunyang,FAN Yong,et al. Flame detectionbased on bidimensional empirical mode decomposition andsupport vector machine[J]. Journal of Changzhou University(Natural science edition),2017,29(2):71?77.
[12]严云洋,杜静,高尚兵,等.融合多特征的视频火焰检测[J].计算机辅助设计与图形学学报,2015,27(3):433?440.YAN Yunyang, DU Jing, GAO Shangbing, et al. Videoflame detection based on fusion of multi?feature[J]. Journal ofcomputer?aided design&computer graphics,2015,27(3):433?440.
[2] JIANG B,LU Y,LI X,et al. Towards a solid solution of real?time fire and flame detection[J]. Multimedia tools and applica?tions,2015,74(3):689?705.
[3] LI H. Research on a new photoelectric detection method to anti?muzzle′s flame or light disturbance and projectile′s informa?tion recognition in photoelectric detection target[J]. Optoelec?tronics and advanced materials?rapid communications,2014,8(7):653?658.
[4] LI Z,ISUPOVA O,MIHAYLOVA L,et al. Autonomous flamedetection in video based on saliency analysis and optical flow[C]//Proceedings of IEEE International Conference on Multisen?sor Fusion and Integration for Intelligent Systems. Baden?Baden:IEEE,2016:218?223.
[5] DIMITROPOULOS K,BARMPOUTIS P,GRAMMALIDIS N.Spatio?temporal flame modeling and dynamic texture analysisfor automatic video?based fire detection[J]. IEEE transactionson circuits and systems for video technology,2015,25(2):339?351.
[6] TOULOUSE T,ROSSI L,CELIK T,et al. Automatic fire pix?el detection using image processing:a comparative analysis ofrule?based and machine learning?based methods[J]. Signal,im?age and video processing,2016,10(4):647?654.
[7] MAHDIPOUR E, DADKHAH C. Automatic fire detectionbased on soft computing techniques:review from 2000 to 2010[J]. Artificial intelligence review,2014,42(4):895?934.
[8] HAN T,LIN B. Research on flame image recognition methodinnaturalscene[C]//ProceedingsofIEEEInternationalConferenceon Information and Automation. Ningbo:IEEE,2016:1776?1780.
[9] ZHAO X,KONG W,WEI J,et al. Gas chromatography withflame photometric detection of 31 organophosphorus pesticideresidues in Alpinia oxyphylla dried fruits[J]. Food chemistry,2014,162:270?276.
[10]宋宁,强彦,董林佳.林火监测中基于视觉的火焰检测方法[J].科学技术与工程,2017,17(25):268?273.SONG Ning,QIANG Yan,DONG Linjia. Vision based flamedetection method in forest fire monitoring[J]. Science tech?nology and engineering,2017,17(25):268?273.
[11]戴静,严云洋,范勇,等.基于BEMD和SVM的火焰检测算法[J].常州大学学报(自然科学版),2017,29(2):71?77.DAI Jing,YAN Yunyang,FAN Yong,et al. Flame detectionbased on bidimensional empirical mode decomposition andsupport vector machine[J]. Journal of Changzhou University(Natural science edition),2017,29(2):71?77.
[12]严云洋,杜静,高尚兵,等.融合多特征的视频火焰检测[J].计算机辅助设计与图形学学报,2015,27(3):433?440.YAN Yunyang, DU Jing, GAO Shangbing, et al. Videoflame detection based on fusion of multi?feature[J]. Journal ofcomputer?aided design&computer graphics,2015,27(3):433?440.