基于改进FCM聚类算法的隧道火灾受困人员信息化定位方法 |
点此下载全文 |
引用本文:崔鹏飞.基于改进FCM聚类算法的隧道火灾受困人员信息化定位方法[J].计算技术与自动化,2022,(3):82-87 |
摘要点击次数: 218 |
全文下载次数: 0 |
|
|
中文摘要:为了缓解火灾现场受困人员定位时间长以及定位精度低的问题,研究基于改进FCM聚类算法的隧道火灾受困人员信息化定位方法。采用改进FCM聚类算法分割隧道火灾图像,利用SIFI算法提取完成分割后隧道火灾图像的空间特征,利用Gabor小波方法获取隧道火灾图像空间特征内的面积边缘以及烟雾纹理,建立方向角分布模型以及烟雾变化能量模型,利用所建立模型提取受困人员的动态特性,实现隧道火灾受困人员的信息化定位。实验结果表明,该方法可以有效定位隧道重大火灾、较大火灾以及一般火灾的受困人员,不同火灾烟雾浓度系数的定位精度均高于98.5%,定位时间低于200 ms。 |
中文关键词:改进 FCM聚类算法 隧道火灾 受困人员 信息化 定位方法 |
|
Informatization Localization Method for People Trapped in Tunnel Fire Based on Improved FCM Clustering Algorithm |
|
|
Abstract:In order to alleviate the problems of long positioning time and low positioning accuracy of tunnel fire victims, an information positioning method of tunnel fire victims based on improved FCM clustering algorithm is studied. The improved FCM clustering algorithm is used to segment the tunnel fire image, the Sifi algorithm is used to extract the spatial features of the segmented tunnel fire image, the Gabor wavelet method is used to obtain the area edge and smoke texture in the spatial features of the tunnel fire image, the direction angle distribution model and smoke change energy model are established, and the dynamic characteristics of the trapped people are extracted by the established model, realize the information positioning of tunnel fire trapped personnel. The experimental results show that this method can effectively locate the trapped people in major fire, large fire and general fire in the tunnel. The positioning accuracy of different fire smoke concentration coefficients is higher than 98.5%, and the positioning time is less than 200 ms. |
keywords:improvement FCM clustering algorithm tunnel fire trapped persons informatization positioning method |
查看全文 查看/发表评论 下载pdf阅读器 |