一种基于飘动性分析的视频烟雾检测新方法

王涛; 刘渊; 谢振平

doi:10.3724/SP.J.1146.2010.00912

一种基于飘动性分析的视频烟雾检测新方法

doi: 10.3724/SP.J.1146.2010.00912

基金项目:

江苏省科技支撑计划项目(BE2008009)资助课题

计量
- 文章访问数: 3464
- HTML全文浏览量: 129
- PDF下载量: 2329
- 被引次数: 0
出版历程
- 收稿日期: 2010-08-27
- 修回日期: 2010-12-07
- 刊出日期: 2011-05-19

Flutter Analysis Based Video Smoke Detection

摘要

摘要: 该文通过对烟雾飘动特性的分析，提出一种基于视频图像的火灾烟雾检测新方法。首先利用滑动时间窗分析视频中运动区域的飘动性特征，提取出飘动方向、周期飘动强度、周期有效飘动强度和周期逆向飘动强度等特征向量；然后使用神经模糊推理系统训练并检测烟雾。与利用其它特征检测烟雾算法的对比实验表明，该算法具有较好的ROC (Receiver Operating Characteristic)曲线特性，具备较高的实际使用价值。
- 图像处理 /
- 视频烟雾检测 /
- 飘动性分析 /
- 神经模糊推理系统 /
- ROC曲线
Abstract: Based on the flutter characteristic of smoke, a novel video smoke detection algorithm is proposed. Firstly, the motion region is detected from video frames. Then four flutter features of the motion region are extracted over a sliding time window, including the flutter direction and three types of flutter intensities. Finally, the neuro-fuzzy inference system is used to detect smoke, in which fuzzy rules and membership functions are trained according to the valid sample set. Experimental results show that the new algorithm has excellent performance on Receiver Operating Characteristic (ROC) curve which is very important for real application.
- Image processing /
- Video smoke detection /
- Flutter analysis /
- Neuro-fuzzy inference system /
- Receiver Operating Characteristic (ROC) curve

HTML全文

参考文献(1)

袁非牛, 张永明, 刘士兴, 等. 基于累积量和主运动方向的视频烟雾检测方法[J]. 中国图象图形学报, 2008, 13(4): 808-813.Yuan Fei-niu, Zhang Yong-ming, and Liu Shi-xing, et al.Video smoke detection based on accumulation and main motion orientation[J]. Journal of Image and Graphics, 2008, 13(4): 808-813.[2] Yuan Fei-niu. A fast accumulative motion orientation model based on integral image for video smoke detection[J]. Pattern Recognition Letters, 2008, 29(7): 925-932.[3] 练秋生, 李党. 融合多种特征的烟雾图像检测算法[J]. 光学技术, 2009, 35(4): 523-534.Lian Qiu-sheng and Li Dang. A smoke detection algorithm combined multiple properties[J]. Optical Technique, 2009, 35(4): 523-534.[4] Ugur Toreyin, Yigithan Dedeoglu, and Ugur Gudukbay, et al.. Computer vision based method for real-time fire and flame detection[J]. Pattern Recognition Letters, 2006, 27(1): 49-58.[5] 杨猛, 赵春晖, 潘泉, 等. 基于小波分析的烟雾多特征融合和空间精度补偿森林火情检测算法[J]. 中国图象图形学报, 2009, 14(4): 694-700.Yang Meng, Zhao Chun-hui, and Pan Quan, et al.Forest-fire detection algorithm based on multiple features fusion by wavelet analysis and spatial accuracy compensation[J]. Journal of Image and Graphics, 2009, 14(4): 694-700.[6] Gonzalez R, Aquino A, and Romero R, et al.. Wavelet-based smoke detection in outdoor video sequences[C]. The 53rd IEEE International Midwest Symposium on Circuits and Systems, Seattle, USA, 1-4 August, 2010: 383-387.[7] Kim Dong-keun and Wang Yuan-fang. Smoke detection in video[C]. World Congress on Computer Science and Information Engineering, Los Angeles, USA, March 31-April 2, 2009, 5: 759-763.[8] Chen Thou-ho (Chao-ho), Yin Yen-hui, and Huang Shi-feng, et al.The smoke detection for early fire-alarming system base on video processing[C]. IEEE International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Pasadena, California, USA, December 18-20, 2006: 427-430.[9] Yang Jing, Chen Feng, and Zhang Wei-dong. Visual-based smoke detection using support vector machine[C]. Fourth International Conference on Natural Computation, Jinan, China, August 25-27, 2008, 4: 301-305.[10] Wei Zheng, Wang Xin-gang, and An Wen-chuan. Target- tracking based early fire smoke detection in video[C]. International Conference on Image and Graphics, Xi'an, China, September 21-24, 2009: 172-176.[11] 王冰, 职秦川, 张仲选, 等. 灰度图像质心快速算法[J]. 计算机辅助设计与图形学学报, 2004, 16(10): 1360-1365.Wang Bing, Zhi Qin-chuan, and Zhang Zhong-xuan, et al.Computation of center of mass for gray level image based on differential moments factor[J]. Journal of Computer-Aided Design Computer Graphics, 2004, 16(10): 1360-1365.[12] Takagi T and Sugeno M. Fuzzy identification of systems and its applications to modeling and control[J]. IEEE Transactions on Systems, Man, Cysbernetics, 1985, 15(1): 116-132.[13] 邹洪侠, 秦锋, 程泽凯, 等. 二类分类器的ROC曲线生成算法[J]. 计算机技术与发展, 2009, 19(6): 109-112.Zou Hong-xia, Qin Feng, and Cheng Ze-kai, et al.Algorithm for generating ROC curve of two-classifier[J]. Computer Technology and Development, 2009, 19(6): 109-112.

施引文献

资源附件(0)

访问统计