| 摘要: |
| 针对烟雾稀薄的场景提出了一种新颖且具有鲁棒性的视频烟雾检测方法，该方法主要由预处理、特征提取和图像分类三个阶段组成。在预处理阶段，使用背景差分算法提取视频帧的运动前景区域，并采用HSV颜色空间作用于运动前景区域识别烟雾像素；然后使用局部极值共生模式(Local Extrema Co-occurrence Pattern，LECoP）计算纹理特征和使用烟雾能量分析计算能量特征；最后，将特征矢量融合训练支持向量机（Support Vector Machine，SVM）用于识别烟雾。实验结果表明该方法能有效检测出烟雾。 |
| 关键词: 烟雾检测 运动前景 能量分析 局部极值共生模式 支持向量机 |
| DOI： |
|
| 基金项目: |
|
| Smoke detection using local extrema co-occurrence pattern and energy analysis |
| YUAN Mei,QUAN Taifeng,HUANG Yang |
| (School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China) |
| Abstract: |
| A novel and robust video-based smoke detection approach for the scene of thin smoke is proposed.The method mainly consists of three phases,namely preprocessing stage,feature extraction stage and image classification stage.In the preprocessing stage,the motion foreground area of the video frame is extracted by using the background subtraction algorithm,and the smoke pixels are identified by the HSV color space used in the motion foreground area.During the next phase,the texture features are computed using local extrema co-occurrence pattern(LECoP) and the smoke energy features are computed using smoke energy statistics.Finally,the two features are fused to a feature vector,which is fed to a support vector machine(SVM) to identify smoke data.The experimental results show that the proposed method can detect smoke effectively. |
| Key words: smoke detection motion foreground energy analysis local extrema co-occurrence pattern support vector machine |
《电讯技术》编辑部 