基于多特征融合的烟雾检测.PDF

2015 年 8 月 图 学 学 报 August 2015 第 36 卷 第4 期 JOURNAL OF GRAPHICS Vol.36 No.4 基于多特征融合的烟雾检测 1 1 2 1 1 吴冬梅 ， 李白萍 ， 沈 燕 ， 王 静 ， 何 蓉 (1. 西安科技大学通信学院，陕西 西安 710054 ；2. 江苏省环境监测中心，江苏 南京 210004) 摘 要：针对传统火灾探测技术的应用弱点，研究基于视频的火灾烟雾探测方法。首先， 根据烟雾的颜色特征，提取视频序列中的疑烟区域。然后，在疑烟区域中提取烟雾的 3 个动态 特征——扩散特征、轮廓不规则特征和使背景模糊特征。最后，利用BP 神经网络对这些动态特 征进行融合判定。实验结果表明，基于多特征融合的烟雾检测方法能够准确、实时、有效地识 别视频中的烟雾。 关 键 词：烟雾；颜色特征；动态特征；BP 神经网络 中图分类号：TP 391 文献标识码：A 文 章 编 号：2095-302X(2015)04-0587-06 Smoke Detection Based on Multi-Feature Fusion 1 1 2 1 1 Wu Dongmei , Li Baiping , Shen Yan , Wang Jing , He Rong (1. Department of Communication, Xi′an University of Science and Technology, Xi′an Shaanxi 710054, China; 2. Jiangsu Envoronmental Monitoring Center, Nanjing Jiangsu 210004, China) Abstract: A new smoke detection method based on video is researched due to the weakness of the traditional fire detection technology. Firstly, according to the characteristic of the smoke color, the suspect smoke regions are extracted in video sequences. Then, looking for three dynamic characteristics of smoke in the suspected smoke area, there are three features extracted, which respectively are the growth of the area in the smoke spread, irregular contour feature of the smoke region and the background to blurred when smoke appeared. And those three dynamic characteristics are fused by a BP neural network to determine smoke or not. Test results show that the multi-feature fusion smoke detection algorithm can identify smoke in