基于BEMD和SVM的火焰检测算法

Fire Detection Based on Bidimensional Empirical Mode Decomposition and Support Vector Machine

为提高火焰检测的准确性,提出了一种采用二维经验模式(BEMD)和支持向量机(SVM)的火焰检测算法。首先基于累积差分法检测运动目标,根据Ohta颜色空间找出图像中具有火焰颜色的疑似区域;其次将疑似区域图像经过BEMD分解,结合局部二值模式(LBP)对所提取到的固有模态函数(IMF)图像进行纹理特征提取;最后将提取的纹理特征结合圆形度、矩形度、重心高度输入到SVM里面进行火焰的判别。实验结果表明该方法具有较高的火焰检测率以及较低的误检率。

In order to improve the accuracy of fire detection,a fire detection algorithm based on Bidimensional Empirical Mode Decomposition（ BEMD） and Support Vector Machine（ SVM） is proposed.Firstly,candidate fire regions were detected based on the accumulative difference method for detecting moving targets and Ohta color space with color model of flame.Secondly,a new method combining the bidimensional empirical mode decomposition（ BEMD） with local binary pattern（ LBP） is proposed for texture image classification.The LBP is used to extract the features of a series of various intrinsic mode functions（ IMFS） images and residual images,which are decomposed by bidimensional empirical mode from the image.Finally,the roundness,rectangle degree,height of center of gravity,texture features are input into the SVM classification.The experimental results show that this method has high flame detection rate,low false alarm rate.