计算机科学 ›› 2015, Vol. 42 ›› Issue (Z6): 231-235.
林涛,黄继风,高建华
LIN Tao, HUANG Ji-feng and GAO Jian-hua
摘要: 在不确定的复杂环境下,基于图像的火焰早期检测是一个未解难题。因此,将灰度均衡化理论延伸至此领域来对疑似火焰图像进行预处理,通过引入SIFT算法发现火焰图像的多尺度特征,确定火焰极值点并进行特征匹配,有效识别火焰尖角以提高侦测的有效性。将分形理论的分数维作为火焰的特征加以使用。由于通常情况下火焰是异常值,一类分类器具有代价低、特征易获取、精度高等诸多优点,因此使用一类分类器完成火焰识别。实验证明,该研究不仅在近距离光照强的条件下具有良好的真阳性率和假阳性率,而且在光照弱的情况下具有较高的火焰发现率和较低的虚警率。
[1] Mueller M,Karasev P,Kolesov I,et al.Optical Flow Estimation for Flame Detection in Videos[J].IEEE Transactions on Image Processing,2013,22(7):2786-2797 [2] Freire G,Castelo Branco K,Machado J M,et al.Local data fusion algorithm for fire detection through mobile robot[C]∥2013 14th Latin American.Cordoba:Test Workshop(LATW).2013 [3] Chmelar P,Benkrid A.Efficiency of HSV over RGB Gaussian Mixture Model for fire detection[C]∥2014 24th International Conference Bratislava:Radioelektronika(RADIOELEKTRONIKA).2014 [4] Dimitropoulos K,Barmpoutis P,Grammalidis N.Spatio-Temporal Flame Modeling and Dynamic Texture Analysis for Automatic Video-Based Fire Detection[J].IEEE Transactions on Circuits and Systems for Video Technology,2014,(99):1 [5] Lowe D G.Distinctive Image Features from Scale-Invariant Keypoints[J].International Journal of Computer Vision,2004,60(2):91-110 [6] 马正华,顾苏杭,戎海龙.基于SIFT特征匹配的CamShift运动目标跟踪算法[J].计算机科学,2014,41(6):291-294 [7] Do Y.Flame detection in grey-scale images of a B/W camera.[J].Sensor Review,2014,34(1):80-88 [8] Punzo G,Karagiannakis P,Bennet D J,et al.Enabling and Exploiting Self-Similar Central Symmetry Formations[J].IEEE Transactions on Aerospace and Electronic Systems,2014,50(1):689-703 [9] Thou-Ho C,Cheng-Liang K,Sju-Mo C.An intelligent real-time fire-detection method based on video processing[C]∥IEEE 37th Annual 2003 International Carnahan Conference on Security Technology,2003.2003 [10] Ti N,Thuan N,Tuan D.Fire detection based on video processing method[C]∥2013 International Conference on Ho Chi Minh City:Advanced Technologies for Communications(ATC).2013 [11] Tax D M J,Duin R P W.Support vector domain description[J].Pattern Recognition Letters,1999,20(11/13):1191-1199 [12] Ganesan K,Acharya U R,Chua C K,et al.One-Class Classification of Mammograms Using Trace Transform Functionals[J].IEEE Transactions on Instrumentation and Measurement,2014,63(2):304-311 |
No related articles found! |
|