结合FCM聚类与SVM的火焰检测算法  

Fire detection algorithm using FCM clustering and SVM

作　　者：李庆辉[1] 李艾华[1] 苏延召[1] 马治明[2] 

机构地区：[1]第二炮兵工程大学502教研室 [2]中国人民解放军96111部队

出　　处：《红外与激光工程》2014年第5期1660-1666,共7页Infrared and Laser Engineering

基　　金：国家自然科学基金(61132008)

摘　　要：针对传统视频型火焰检测算法误报率高、局限性强等问题,提出一种四步火焰检测算法。首先利用一种自适应混合高斯模型(GMM)检测视频序列中的运动目标;然后采用模糊C均值(FCM)聚类算法分割疑似火焰区域与非火区域;再提取疑似火焰区域的面积变化、表面不均度等时空特征参数;最后将这些特征参数输入训练好的支持向量机(SVM)分类器以识别火焰区域。实验结果表明,算法不但在提高了检测率的同时降低了误检率,而且适用范围广,是一种有效的火焰检测算法。An effective, four-stage fire-detection algorithm used to automatically detect fire in video images was presented in this paper. An adaptive Gaussian mixture model was used to detect moving regions in a video clip. A fuzzy C- means （FCM） algorithm was adopted to segment the candidate fire regions （fire and fire-colored objects） from these moving regions based on the color of fire. Some special parameters were extracted based on the tempo-spatial characteristics of fire regions; these parameters included the area randomness, surface roughness and motion estimation of fire. Finally, these parameters extracted from the third stage were used as input feature vectors to train a support vector machine（SVM） classifier, which was then used by the fire alarm to distinguish between fire and non-fire. Experimental results indicate that the proposed method outperforms other fire detection algorithms, providing high reliability and a low false alarm rate.

关 键 词：火焰检测 混合高斯模型 模糊C均值聚类 支持向量机 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]