Please wait a minute...
浙江大学学报(工学版)
J4  2012, Vol. 46 Issue (4): 698-704    DOI: 10.3785/j.issn.1008-973X.2012.04.018
自动化技术、电信技术     
具有高区分度的视频火焰检测方法
谢迪1, 童若锋1, 唐敏1, 冯阳2
1.浙江大学 计算机科学与技术学院,浙江 杭州 310027；
2.浙江警察学院 计算机科学与技术学院,浙江 杭州  310053
Distinguishable method for video fire detection
XIE Di1, TONG Ruo-feng1, TANG Min1, FENG Yang2
1. College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China;
2. College of Computer Science and Technology, Zhejiang Police College, Hangzhou 310053, China
 全文: PDF 
摘要：

为了在视频监控系统中准确地判断火焰区域并预测火灾的发生,提出一种新的基于人工神经网络的视频火焰检测方法.该方法在分析火焰的运动和三维颜色特征的基础上,分别通过傅里叶变换和圆形度分析、角点检测的方法研究火焰的闪烁频率、几何形状对应的时空域特征,采用获得的各类特征构成概率向量作为人工神经网络分类模型的输入,输出表示火灾发生的概率.在保持检测准确率的同时,该方法通过实验选择最优的参数组合解决神经网络容易陷入局部极值及收敛慢的问题.该方法可以区分大空间（隧道、仓库、博物馆等建筑物）中闪烁的车灯和真实火焰,能够避免在实际的视频监控系统应用中将闪烁车灯误判为火焰,有效减少环境光对检测结果的影响,降低火灾火焰的误报率.实验结果表明,采用该方法在保持检测实时性的同时,能够达到96%的检测正确率.
关键词： 火焰检测;  人工神经网络;  傅里叶变换;  圆形度;  角点检测;  多变量高斯模型;  分层k-means    
Abstract:

A novel method for video fire detection based on artificial neural network was proposed in order to estimate fire regions and predict occurrence of fire in video surveillance system. Temporal-spatial features were analyzed including flicker frequency and geometry of fire by Fourier transformation, roundness degree analysis and corner detection based on motion and three-dimensional color features. Then these features were used as a probability vector fed for artificial neural network classification model to output the probability of fire. With keeping accurate detection rate, two problems, local extremum tendency and slow convergence rate, of artificial neural network were solved by optimal parameters combination experimentally. The method can distinguish flickering vehicle light from actual fire in varied locations, e.g. tunnel, warehouse and museum, to prevent ambiguity and eliminate the influence environment illumination imposing onto the detection results which significantly reduce false positive rate. Experimental results show that the method has a 96% detection rate while keeping a real-time performance.
Key words: fire detection    artificial neural network    Fourier transformation    roundness degree    corner detection    multivariate Gaussian model    hierarchical k-means
出版日期: 2012-05-02
:  TP 391.41  
基金资助:

浙江省科技厅优先主题重点社会发展资助项目（2010C13023）；浙江省自然科学基金资助项目（Y1100018）.
通讯作者: 童若锋,男,教授.     E-mail: trf@zju.edu.cn
作者简介: 谢迪(1985—),男,博士生,从事视频图像处理、计算机视觉的研究.E-mail: xdrabbite@zju.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

谢迪, 童若锋, 唐敏, 冯阳. 具有高区分度的视频火焰检测方法[J]. J4, 2012, 46(4): 698-704.

XIE Di, TONG Ruo-feng, TANG Min, FENG Yang. Distinguishable method for video fire detection. J4, 2012, 46(4): 698-704.

链接本文:

http://www.zjujournals.com/xueshu/eng/CN/10.3785/j.issn.1008-973X.2012.04.018    或    http://www.zjujournals.com/xueshu/eng/CN/Y2012/V46/I4/698

［1］ HEALEY G, SLATER D, LIN T, et al. A system for realtime fire detection ［C］∥ IEEE Computer Vision and Pattern Recognition Conference. New York: IEEE, 1993: 605-606.
［2］ PHILLIPS W, SHAH M, LOBO N. Flame recognition in video ［C］∥ Proceedings of the 5th IEEE Workshop on Applications of Computer Vision. Palm Springs: IEEE, 2000: 224-229.
［3］ LIU C B, AHUJA N. Vision based fire detection ［C］∥ IEEE International Conference on Pattern Recognition. Washington DC: IEEE, 2004: 134-137.
［4］ TOREYIN B U, DEDEOGLU Y, GUDUKBAY U, et al. Computer vision based method for realtime fire and flame detection ［J］. Pattern Recognition Letters, 2006, 27(1): 49-58.
［5］ TOREYIN B U, DEDEOGLU Y, GUDUKBAY U, et al. Realtime fire and flame detection in video ［C］∥ International Conference on Acoustics Speech, and Signal Processing. Philadelphia: IEEE, 2005: 669-672.
［6］ TOREYIN B U, DEDEOGLU Y, CETIN A E. Flame detection in video using hidden Markov models ［C］∥ International Conference on Image Processing. Genoa: IEEE, 2005: 1230-1233.
［7］ TOREYIN B U, CETIN A E. Online detection of fire in video ［C］∥ IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis: IEEE, 2007: 1-5.
［8］ KO B C, CHEONG K H, NAM J Y. Fire detection based on vision sensor and support vector machines ［J］. Fire Safety Journal, 2009, 44(3): 322-329.
［9］ CELIK T, DEMIREL H. Fire detection in video sequences using a generic color model ［J］. Fire Safety Journal, 2009, 44(2): 147-158.
［10］ HO C C, KUO T H. Realtime videobased fire smoke detection system ［C］∥ IEEE International Conference on Advanced Intelligent Mechatronics. Singapore: IEEE, 2009: 1845-1850.
［11］ GUNAY O, TASDEMIR K, TOREYIN B U. Video based wild fire detection at night ［J］. Fire Safety Journal, 2009, 44(6): 860-868.
［12］ TOREYIN B U, CETIN A E. Wildfire detection using LMS based active learning ［C］∥ International Conference on Acoustics Speech, and Signal Processing. Taipei: IEEE, 2009: 1461-1464.
［13］ COLLINS R T, LIPTON A J, KANADE T, et al. A system for video surveillance and monitoring ［R］. Pittsburgh: Robotics Institute, 1999.
［14］ NISTER D, STEWENIUS H. Scalable recognition with a vocabulary tree ［C］∥ Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2006: 2161-2168.
［15］ SUZUKI S, ABE K. Topological structural analysis of digitized binary images by border following ［J］. Computer Vision, Graphics, and Image Processing, 1985, 30(1):32-46.
［16］ HARRIS C, STEPHENS M. A combined corner and edge detector ［C］∥ Proceedings of the Alvey Vision Conference. Manchester: ［s. n.］, 1988: 147-151.
［17］ BALABIN R M, LOMAKINA E I. Neural network approach to quantumchemistry data: accurate prediction of density functional theory energies ［J］. Journal of Chemistry and Physics, 2009, 131(7): 74-104.
［18］ BISHOP C M. Pattern recognition and machine learning ［M］. New York: Springer, 2006: 232-241.
[1] 张心怡, 杨家强, 张晓军. 基于机会约束的含多风电场动态经济调度[J]. 浙江大学学报(工学版), 2017, 51(5): 976-983.
[2] 黄赠, 王锐, 赵宇, 魏振磊. 隐伏断层地震诱发滑坡易发性评价[J]. 浙江大学学报(工学版), 2017, 51(11): 2136-2143.
[3] 江衍铭, 张建全, 明焱. 集合神经网络的洪水预报[J]. 浙江大学学报(工学版), 2016, 50(8): 1471-1478.
[4] 刘凯, 张立民, 张超. 受限玻尔兹曼机的新混合稀疏惩罚机制[J]. 浙江大学学报(工学版), 2015, 49(6): 1070-1078.
[5] 麻剑, 谢阳, 罗麒元, 许沧粟. 精制生物油和柴油混合燃料的柴油机性能[J]. 浙江大学学报(工学版), 2015, 49(4): 632-637.
[6] 楼文娟,王嘉伟,杨伦,陈勇. 雷暴风三维脉动风速场数值模拟[J]. 浙江大学学报(工学版), 2014, 48(7): 1162-1169.
[7] 柯海丰,应晶. 基于R-ELM的实时车牌字符识别技术[J]. 浙江大学学报(工学版), 2014, 48(7): 1209-1216.
[8] 柯海丰,应晶. 基于R-ELM的实时车牌字符识别技术[J]. J4, 2014, 48(2): 0-0.
[9] 张进高,卢琴芬,王利,叶云岳, 洪伟明. 基于FFT的直线电机地铁牵引电机功率因数角测量[J]. J4, 2012, 46(11): 1981-1984.
[10] 金文光, 张正宇, 唐少华. 2FSK信号DSTFT解调算法中的同步新方法[J]. J4, 2011, 45(6): 1027-1031.
[11] 任沙浦, 沈国江. 短时交通流智能混合预测技术[J]. J4, 2010, 44(8): 1473-1478.
[12] 竺乐庆, 陈文智, 幸锐, 等. 鲁棒的掌纹图像特征提取方法[J]. J4, 2009, 43(8): 1412-1418.
[13] 孔祥杰, 沈国江, 梁同海. 具有公交优先的路网交通流智能协调控制[J]. J4, 2009, 43(6): 1026-1031.
[14] 谭大鹏 李培玉 潘晓弘. 基于振动信号测量的连铸下渣检测系统[J]. J4, 2008, 42(8): 1399-1403.
[15] 王强 潘翔. 水下沉底小目标回波的短时FrFT滤波分析[J]. J4, 2008, 42(6): 918-922.