摘要
论文针对传统火焰颜色检测上存在的模型缺陷,提出一种基于RGB颜色通道的高斯分布模型。根据火焰图像R通道像素值分布在其平均值周围的不对称程度定义一种火焰图像的偏度。然后引入了自下而上的视觉显著性概念,先从视频帧序列火焰图像中求得图像的局部显著性,全局显著性,稀疏显著性这三个初阶段图像特征图谱,对这三个求得特征图谱进行加权融合,得到的综合火焰显著性图来表征火焰的候选区域。最后提取火焰的空间结构,区域几何等特征,用支持向量机进行最终的分类判别。实验结果表明,论文算法准确率较高,且抗干扰能力强。
In this paper,a Gauss distribution model based on RGB color channel is proposed in view of the model defects in the traditional flame color detection.The skewness of a flame image is defined according to the asymmetry of the R channel pixel values distributed around the average value of the flame image.Then it introduces the concept of visual saliency from bottom to top.First,the three initial stage image features of the image are obtained from the video frame sequence,which are local saliency,global saliency and sparsity.Then the three characteristic maps are weighted together,and the comprehensive flame saliency map is obtained to represent the candidate region of the flame.Finally,the space structure of the flame and the characteristics of the region geometry are extracted,and the final classification and discrimination are carried out by the support vector machine.The experimental results show that the accuracy of the algorithm is high and the anti-interference ability is strong.
作者
张楠波
俞孟蕻
黄炜亮
李袁
ZHANG Nanbo;YU Menghong;HUANG Weiliang;LI Yuan(School of Computer,Jiangsu University of Science and Technology,Zhenjiang 212000)
出处
《计算机与数字工程》
2019年第8期2039-2043,共5页
Computer & Digital Engineering
关键词
火焰检测
视觉显著性
特征提取
支持向量机
fire detection
visual saliency
feature extraction
support vector machine