CAJ | 학술논문

为了有效克服复杂环境下动态、静态疑似烟雾物体的干扰，实现对烟雾的实时准确检测，提出基于混合高斯运动检测模型与多特征分析的烟雾识别算法。首先应用优化的混合高斯运动分析模型对视频图像序列进行运动区域提取，然后依据烟雾的颜色特性、形状不规则性及面积扩散特点，对提取的疑似烟雾运动区域进行分析与筛选，从而判定出其是否为烟雾。实验结果表明：该算法可实时提取视频中的烟雾区域，并有效剔除疑似烟雾区域的干扰，具有良好的烟雾识别能力。
위료유효극복복잡배경하동태、정태의사연무물체적간우，실현대연무적실시준학검측，제출기우혼합고사운동검측모형여다특정분석적연무식별산법。수선응용우화적혼합고사운동분석모형대시빈도상서렬진행운동구역제취，연후의거연무적안색특성、형상불규칙성급면적확산특점，대제취적의사연무운동구역진행분석여사선，종이판정출기시부위연무。실험결과표명：해산법가실시제취시빈중적연무구역，병유효척제의사연무구역적간우，구유량호적연무식별능력。
In order to overcome interference with the similar static or dynamic smoke in complicated environment and realize real-time and accurate smoke detection, a smoke detection algorithm based on Gaussian mixturemodel and multiple features is presented. First, the motion region of video is obtained by modified Gaussian mixturemodel,andis analyzed according to color, irregular shape and diffusion featuresofthe smoke. Then the conclusion is acquired thatthe motion regionisasmokeregion or not. The experimental results show that the algorithm has favorablesmoke detection performance, whichcan acquire real-time smoke information in video and eliminate the interference of similar smoke area.