动态环境下早期烟雾、火苗的视频分级检测研究
|
摘要
视频火灾探测是计算机视觉中一项理论意义与实际价值兼备的重要课题,对烟火事故的消防安全具有重要的实际意义。但由于火灾衍生物的多变性和火灾场景的复杂性,使得火灾的视频探测研究成为一个极具挑战性的工作,目前尚未形成具有普适性的理论和算法。本文主要是进行视频火灾探测方法的研究,旨在提高火灾预警系统的灵敏度,降低误报率,从而更好地对火灾的发生进行早期预警。
全文研究内容主要分成四个部分:背景重建与目标的提取分割,静态特征的提取,动态特征的提取和基于BP神经网络的火灾分级检测。
在对传统的运动目标检测算法进行深入研究的基础上,分析了高斯背景模型等几类算法的基本原理,然后利用适合本文场景的二级背景模型和背景差分方法,结合数学形态学提取出初始目标,从而去除一些静态因素的干扰。在此基础上,通过对大量火灾的烟雾、火焰图像的调查研究,找出烟雾、火焰在特定颜色空间中的分布,建立了相应的颜色模型,分割出类似火焰、烟雾的区域。
本文在对比烟雾、火焰及干扰物的动态特征的基础上,分析了所得分割区域的运动累积量、闪烁规律、运动方向、运动一致性、运动程度等火灾判据,并给出了各种判据的分析和计算方法。讨论了基于BP神经网络的动态特征判据融合方案,首先简单介绍了人工神经网络的内容,随后给出了本文神经网络的特征定义、输入输出单元及设计方案,并利用设计的神经网络实现了动态环境下早期火灾的分级检测。
本文采用25个不同条件下的视频作为样本进行训练,并利用训练好的神经网络测试另外的35个视频,其中,有两个视频出现漏判,一个视频出现误判。结果表明,本文方法能在200帧内有效地识别出早期烟雾、火焰,并可以抵抗常见干扰对系统的影响,较好地实现了识别系统的鲁棒性与敏锐性的统一。
Video fire detection is one of the most active research topics being valuable for both theoretical and practical research in computer vision especially has a wide spectrum of promising applications in video surveillance for early fire alarms in public security. However, because of the polytropy of the fire derivatives and complexity of scene, video fire detection becomes a difficult problem with large challenges, yet there are no general theories or algorithms have formed so far. In this paper, it is mainly research the methodology of video fire detection, in order to improve the sensitivity of fire alert system and reduce false alarm, so as to promote the performance of video fire detection system.
The research contents of this paper are mainly composed of 4 parts: background-rebuild and moving object extraction, static features extraction, dynamic features extraction, fire grading-detection base on BP neural network.
The principle of Gaussian and some other background models are analyzed on the basis of further study on traditional moving detection algorithms and, then the two step background model which is suitable for this paper is selected to extract the initial object, combine with background subtraction and mathematical morphology, and thus remove the static interferences. After extracting the moving region the distribution in specific color space of flame and smoke are found by investigation on flame and smoke images, and the corresponding color models are build to segment the flame and smoke like regions.
The motion accumulation, flicker frequency, motion orientation, motion consistency, motion degree, etc, those dynamic criterions of the segment regions are analyzed based on comparisons between flame, smoke and other disturbing objects, more over, the analysis and computation methods of the criterions are brought forward. The fire criterions fusion scheme based on BP neural network is discussed, firstly, the basic contents of artificial neural network is introduced, and then the definition of characters, the input/output unit and design scheme of BP neural network are presented, at last, the designed neural network is used for grading-detection of early smoke and flame images.
25 video clips under different condition are used for training neural network and, the neural network is used for recognizing other 35 video clips, among these, only 2 video clips are missed and 1 video clips is error recognized. The results show that the system can recognize the flame and smoke in 200 frames and has good anti-interference ability.
全文研究内容主要分成四个部分:背景重建与目标的提取分割,静态特征的提取,动态特征的提取和基于BP神经网络的火灾分级检测。
在对传统的运动目标检测算法进行深入研究的基础上,分析了高斯背景模型等几类算法的基本原理,然后利用适合本文场景的二级背景模型和背景差分方法,结合数学形态学提取出初始目标,从而去除一些静态因素的干扰。在此基础上,通过对大量火灾的烟雾、火焰图像的调查研究,找出烟雾、火焰在特定颜色空间中的分布,建立了相应的颜色模型,分割出类似火焰、烟雾的区域。
本文在对比烟雾、火焰及干扰物的动态特征的基础上,分析了所得分割区域的运动累积量、闪烁规律、运动方向、运动一致性、运动程度等火灾判据,并给出了各种判据的分析和计算方法。讨论了基于BP神经网络的动态特征判据融合方案,首先简单介绍了人工神经网络的内容,随后给出了本文神经网络的特征定义、输入输出单元及设计方案,并利用设计的神经网络实现了动态环境下早期火灾的分级检测。
本文采用25个不同条件下的视频作为样本进行训练,并利用训练好的神经网络测试另外的35个视频,其中,有两个视频出现漏判,一个视频出现误判。结果表明,本文方法能在200帧内有效地识别出早期烟雾、火焰,并可以抵抗常见干扰对系统的影响,较好地实现了识别系统的鲁棒性与敏锐性的统一。
Video fire detection is one of the most active research topics being valuable for both theoretical and practical research in computer vision especially has a wide spectrum of promising applications in video surveillance for early fire alarms in public security. However, because of the polytropy of the fire derivatives and complexity of scene, video fire detection becomes a difficult problem with large challenges, yet there are no general theories or algorithms have formed so far. In this paper, it is mainly research the methodology of video fire detection, in order to improve the sensitivity of fire alert system and reduce false alarm, so as to promote the performance of video fire detection system.
The research contents of this paper are mainly composed of 4 parts: background-rebuild and moving object extraction, static features extraction, dynamic features extraction, fire grading-detection base on BP neural network.
The principle of Gaussian and some other background models are analyzed on the basis of further study on traditional moving detection algorithms and, then the two step background model which is suitable for this paper is selected to extract the initial object, combine with background subtraction and mathematical morphology, and thus remove the static interferences. After extracting the moving region the distribution in specific color space of flame and smoke are found by investigation on flame and smoke images, and the corresponding color models are build to segment the flame and smoke like regions.
The motion accumulation, flicker frequency, motion orientation, motion consistency, motion degree, etc, those dynamic criterions of the segment regions are analyzed based on comparisons between flame, smoke and other disturbing objects, more over, the analysis and computation methods of the criterions are brought forward. The fire criterions fusion scheme based on BP neural network is discussed, firstly, the basic contents of artificial neural network is introduced, and then the definition of characters, the input/output unit and design scheme of BP neural network are presented, at last, the designed neural network is used for grading-detection of early smoke and flame images.
25 video clips under different condition are used for training neural network and, the neural network is used for recognizing other 35 video clips, among these, only 2 video clips are missed and 1 video clips is error recognized. The results show that the system can recognize the flame and smoke in 200 frames and has good anti-interference ability.
引文
[1]范维澄,王治安,姜冯辉等.火灾学简明教程[M].合肥:中国科学技术大学出版社,1995.
[2]吴龙标,袁宏永等.火灾检测与控制工程[M].合肥:中国科学技术大学出版社,1999.
[3]陈涛,袁宏永,范维澄.火灾探测技术研究展望[J].火灾科学,2001,10(2):108-112.
[4]贺玉凯,关中辉.火灾探测技术的发展趋势[J].辽宁工学院学报,2004,24(6): 11-14.
[5]王振华.基于视频图像的火灾探测技术的研究[D].西安建筑科技大学硕士学位论文,2008.
[6]黄普希,张昊.国外视频烟雾探测技术简析[J].智能建筑电气技术,2007,1(6):13-16.
[7]孙宇臣,王自朝,葛宝臻.视频火灾探测系统现状分析[J].消防设备研究,2007,26(4):414-417.
[8] H.Yamagishi and J.Yamaguchi. Fire Flame Detection Algorithm Using a Color Camera[J]. Proc of International Symposium on Micro-mechatronics and Human Science. 2003:255-260.
[9] S.Noda, K.Ueda. Fire Detection in Tunnels Using an Image Processing Method[J] . Proceedings of the 1994 Vehicle Navigation and Information System Conference. 2004:57-62.
[10] Phillips III W, Shah M, Lobo N V. Flame recognition in video[J]. Pattern Recognition Letters, 2002, 23 (1-3):319-327.
[11] Dedeoglu Y, Toreyin B U, Gudukbay U, et al. Real-time fire and flame detection in video[J]. In Proc. of IEEE ICASSP’05. 2005: 669-672.
[12] Turgay ?elik, Hüseyin ?zkaramanl?, et al. FIRE AND SMOKE DETECTION WITHOUT SENSORS: IMAGE PROCESSING BASED APPROACH[J]. Journal on Advances in Signal Processing, 2007: 1794-1798.
[13] B. Ugur Toreyin, Yigithan Dedeoglu, A. Enis Cetin. Flame detection in videousing hidden markov models[C]. IEEE International Conference on Image Processing, 2005:1230-1233.
[14] Byoung Chul Ko, Kwang-HoCheong, Jae-YealNam. Fire detection based on vision sensor and support vector machines[J]. Fire Safety Journal, 2009(4): 322-329
[15] Nobuyuki, Fujiwara, Kenji. Terada. Extraction of a Somke Region Using Fractal Cording. Jntemational Symposium on Communication and Information Technologies. October 2004:26-29.
[16] B.Ugur Toreyin, Yigithan Dedeoglu, A. Enis Cetin. Wavelet Based Real-Time Smoke Detection in Video. 13th European Signal Processing Conference EUSIPCO 2005:102-104.
[17] Thou-Ho Chen, Ping-Hsueh Wu, Yung-Chuen Chiou. An Image Processing Based Early Fire Alarming Method with Fuzzy Logic [J]. In Proc. of IEEE ICIP04, 2004: 456-463.
[18] Xueming Shu et al. A new method of laser sheet imaging-based fire smoke detection. Journal of Fire Sciences.2006, 24(2):95-104.
[19] Khananian A, Fraser. R.H., Cihlar J. Automatic detection of fire smoke using artificial neural networks and threshold approaches applied to AVHRR imagery. IEEE Transactions on Geoscience and Remote Sensing. 2001, 39(9):1859-1870.
[20] R.J. Ferrari, H.Zhang, C.R.Kube. Real-time detection of steam in video images Pattern Recognition.2007, 40(3):1148-1159.
[21]陈锋强.复杂场景下运动物体检测与跟踪算法研究[D] .上海交通大学硕士学位论文,2008.
[22] M. Jones.“Variable Kernel Density Estimates”. Australian J. Statisties, 1990.
[23] A.Monnet, A.Mittal, N.Paragios, V.Ramesh. Background Modeling and Subtraction of Dynamic Scenes[C]. IEEE Proe.Int’1Conf.Computer Vision,2003.
[24] K. P. Karmann, A. Brand, Moving object recognition using an adaptive background memory[J]. Time Varying Image Processing and Moving Object Recognition, Vol.2, Elsevier, Amsterdam, The Netherlands, 1990.
[25] C. Stauoer, W. Grimson. Adaptive background mixture models for real-time tracking[J]. Proceedings of the IEEE CS Conference on Computer Vision and Pattern Recognition Vol.2, 1999, PP.246-252.
[26] Verri A, Urass, DeMieheliE. Motion Segmentation from optical flow[C],In:Proc the 5th Alvey Vision Conference, Brighton, UK,1989:209-214.
[27] Barron. J, Fleet. D, Beauehemins. Performance of optical flow techniques[J]. International journal of computer vision, 1994:12(1):42-77.
[28]张玲.视频目标跟踪方法研究[D] .中国科学技术大学博士学位论文,2009.
[29] Haritaoglu. L, Harwood. D, and Davis. L. Real-time surveillance of people and their activities[C]. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(8):809-830.
[30] Kilger M. A shadow handler in a video-based real-time traffic monitoring system[C]. IEEE Proc on Application of Computer Vision. Palm Springs, CA, 1992: 11-18.
[31] Michael harville, Hewlet-Packard Laboratories. A Framework for High-Level Feedback to Adaptive, Per-Pixel, Mixture-of-Gaussian Models[C]. In the 7th European Conference on Computer Vision, May28-31, 2002.
[32] C.R. Wren, A. Azarbayejani, T. Darrell, A. P. Pentland. Real-Time Tracking of the Human Body[J]. IEEE Trans. Pattern Analysis and Machine Intelligence,vol.19,no.7, PP.780-785, July 1997.
[33] Stauffer C, Grimson W. Adaptive background mixture models for real-time tracking[C]. Computer Vision and Pattern Recognition, 1999.IEEE Society Conference, 1992(2):246-252.
[34] Chris Stauffer, W.Eric L.Grimson. Learning Patterns of Activity Using Real-Time Tracking[J]. IEEE Transaction on Pattern and Machine Intelligence, 2000-08, 22(8):747-757.
[35] Z.Zivkovic. Improved Adaptive Gaussian Mixture Model for Background Subtraction[C]. Proe. Int’1Conf. Pattern Recognition,vol.2, PP.28-31, 2004.
[36] Elgammal A., Duraisw ami, R. Harwood. D., DavisL.S. Background and foreground modeling using nonparametric kernel density estimation for visualsurveillance[C] Proceedings of IEEE 90(7), July 2002 Page(s):1151-1163.
[37] K. Toyama, J.Krumm, B.Brumitt, and B. Meyers. Principles and Practice of Background Maintenance[C]. proc. IEEEInt’1Conf. Computer Vision, vol.1, PP.255-261, 1999.
[38] A.Monnet,A.Mittal,N.Paragios, and R.Visvanathan. Background Modeling and Subtraction of Dynamic Scenes[C]. Proe. IEEE Int’1 Conf. Computer Vision, vol.2, PP. 1305-1312, 2003.
[39] J. Kato, T. Watanabe, S.Joga,J. Rittseher, and A. Blake. An HMM-Based Segmentation Method for Traffic Monitoring Movies[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, vol.24,no.9,pp.1291-1296.Sept.2002.
[40] M. Mason and Z. Durie. Using Histograms to Deteet and Track Objects in Color Video[J] . Proc. Applied Imagery Pattern Recognition Workshop, PP.154-159,2001.
[41] Heikkila. M., Pietikainen. M. A texture-based method for modeling the background and detecting moving objects[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on Vol.28, Issue4, April 2006 Page(s):657-662.
[42] R. T. Collins, A. J. Lipton, T. Kanade. A System for Video Surveillance and Monitoring [C]. Proc. of American Nuclear Society 8th Int. Topical Meeting on Robotics and Remote Systems, Pittsburgh, PA, Apr.25-29, 1999.
[43] B. Ugur Toin, Yigithan Dedeoglu, A. Enis Cetin, et al. Computer Vision Based Method for Real-time Fire and Flame Detection. Pattern Recognition Letters 27, pp.49–58, 2006.
[44]周平,姚庆杏,钟取发等.基于视频的早期烟雾检测[J].光电工程,Vol.35,No.12 Dec,2008.82-88.
[45]林学阎,王宏等译.计算机视觉——一种现代方法,2004(6):83-111,326-332.
[46]杨静,陈昭炯.不同颜色空间中全局色彩传递算法的分析研究[J].计算机工程与应用, 2007,43(25):80-82.
[47] C.A. Poynton, A Technical Introduction to Digital Video [M], Wiley, New York, 1996.
[48]郝琳波.基于肤色与脸部特征提取的人脸检测.西安电子科技大学硕士学位论文,2008.
[49] Horng Wen-Bing, Peng Jian-Wen, Chen Chih-Yuan. A new image-based real-time flame detection method using color analysis[C]. Proceedings of the 2005 IEEE international Conference on Networking, Sensing and Control. Tucson, Arizona, USA:IEEE Press,2005:100-105.
[50] Chen Thou-Ho, Wu Ping-Hsueh, Chiou Yung-Chuen. An early fire-detection method based on image processing[C]. Proceedings of the 2004 International Conference on Image Processing, Singapore, IEEE Press, 2004:1707-1710.
[51]袁非牛.基于运动累积量和半透明的视频烟雾探测模型[J].数据采集与处理,2007.22(4):396-400.
[52]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.
[53] Feiniu Yuan. A fast accumulative motion orientation model based on integral image for video smoke detection[J]. Pattern Recognition Letters 29 (2008) :925-932.
[54]贾云得.机器视觉[M] .科学出版社,2002.
[55] M.Ghanbari. The cross-search algorithm for motion estimation, IEEE Trans.On Communication, 1990, 38:950-953.
[56] Koga T, Linuma K, Hirano A, et al. Motion compensated interframe coding for video conferencing[A]. In: Proceedings of National Tele2 communications Conference [ C ] , New Orleans, LA, 1981: G51311-G51315.
[57] Zeng R, Liou M L. A new three-step search algorithm for block motion estimation[J]. IEEE Transactions on Circuits System Video Technology, 1994, 4 (8) : 438-442.
[58] Jain J R, Jain A K. Displacement measurement and its application in inter frame image coding [J]. IEEE Transactions on Communications, 1981, 29 (12) : 1799-1808.
[59] Zhu Shan, Ma Kai Kuang. A new diamond search algorithm for fast block matching motion estimation[J]. IEEE Transactions on Image Processing, 2000, 9(2) : 287～290.
[60] Ziyou Xiong, Rodrigo Caballero, Hongcheng Wang et.al. Video-based Smoke Detection: Possibilities, Techniques, and Challenges Suppression and Detection Research and Applications[C]. In: A Technical Conference(SUPDET 2007), Orlando, Florida(March 5-8,2007).
[61]帅师,周平,汪亚明等.基于小波的实时烟雾检测[J].计算机应用研究,2007,24(3):309-311.
[62]吴龙标,连加锐.基于遗传算法的前馈神经网络火灾探测[J].火灾科学,1998,7(2):21-26.
[63]姚伟祥,吴龙标等.火灾探测的一种模糊神经网络方法[J].自然科学进展,1999,9(8):739-745.
[64]乔继斌.基于图像处理技术的火灾检测[D].沈阳工业大学硕士学位论文,2008.
[65]刘亮亮.基于视频监控的火灾图像识别研究[D].华北电力大学(北京)硕士学位论文,2007.
[66]陈祥光,裴旭东.人工神经网络技术及应用[M].中国电力出版社,2003.
[67]吕普铁.基于普通CCD摄像机的火灾探测技术的研究[D] .哈尔滨.哈尔滨工程大学,2003
[2]吴龙标,袁宏永等.火灾检测与控制工程[M].合肥:中国科学技术大学出版社,1999.
[3]陈涛,袁宏永,范维澄.火灾探测技术研究展望[J].火灾科学,2001,10(2):108-112.
[4]贺玉凯,关中辉.火灾探测技术的发展趋势[J].辽宁工学院学报,2004,24(6): 11-14.
[5]王振华.基于视频图像的火灾探测技术的研究[D].西安建筑科技大学硕士学位论文,2008.
[6]黄普希,张昊.国外视频烟雾探测技术简析[J].智能建筑电气技术,2007,1(6):13-16.
[7]孙宇臣,王自朝,葛宝臻.视频火灾探测系统现状分析[J].消防设备研究,2007,26(4):414-417.
[8] H.Yamagishi and J.Yamaguchi. Fire Flame Detection Algorithm Using a Color Camera[J]. Proc of International Symposium on Micro-mechatronics and Human Science. 2003:255-260.
[9] S.Noda, K.Ueda. Fire Detection in Tunnels Using an Image Processing Method[J] . Proceedings of the 1994 Vehicle Navigation and Information System Conference. 2004:57-62.
[10] Phillips III W, Shah M, Lobo N V. Flame recognition in video[J]. Pattern Recognition Letters, 2002, 23 (1-3):319-327.
[11] Dedeoglu Y, Toreyin B U, Gudukbay U, et al. Real-time fire and flame detection in video[J]. In Proc. of IEEE ICASSP’05. 2005: 669-672.
[12] Turgay ?elik, Hüseyin ?zkaramanl?, et al. FIRE AND SMOKE DETECTION WITHOUT SENSORS: IMAGE PROCESSING BASED APPROACH[J]. Journal on Advances in Signal Processing, 2007: 1794-1798.
[13] B. Ugur Toreyin, Yigithan Dedeoglu, A. Enis Cetin. Flame detection in videousing hidden markov models[C]. IEEE International Conference on Image Processing, 2005:1230-1233.
[14] Byoung Chul Ko, Kwang-HoCheong, Jae-YealNam. Fire detection based on vision sensor and support vector machines[J]. Fire Safety Journal, 2009(4): 322-329
[15] Nobuyuki, Fujiwara, Kenji. Terada. Extraction of a Somke Region Using Fractal Cording. Jntemational Symposium on Communication and Information Technologies. October 2004:26-29.
[16] B.Ugur Toreyin, Yigithan Dedeoglu, A. Enis Cetin. Wavelet Based Real-Time Smoke Detection in Video. 13th European Signal Processing Conference EUSIPCO 2005:102-104.
[17] Thou-Ho Chen, Ping-Hsueh Wu, Yung-Chuen Chiou. An Image Processing Based Early Fire Alarming Method with Fuzzy Logic [J]. In Proc. of IEEE ICIP04, 2004: 456-463.
[18] Xueming Shu et al. A new method of laser sheet imaging-based fire smoke detection. Journal of Fire Sciences.2006, 24(2):95-104.
[19] Khananian A, Fraser. R.H., Cihlar J. Automatic detection of fire smoke using artificial neural networks and threshold approaches applied to AVHRR imagery. IEEE Transactions on Geoscience and Remote Sensing. 2001, 39(9):1859-1870.
[20] R.J. Ferrari, H.Zhang, C.R.Kube. Real-time detection of steam in video images Pattern Recognition.2007, 40(3):1148-1159.
[21]陈锋强.复杂场景下运动物体检测与跟踪算法研究[D] .上海交通大学硕士学位论文,2008.
[22] M. Jones.“Variable Kernel Density Estimates”. Australian J. Statisties, 1990.
[23] A.Monnet, A.Mittal, N.Paragios, V.Ramesh. Background Modeling and Subtraction of Dynamic Scenes[C]. IEEE Proe.Int’1Conf.Computer Vision,2003.
[24] K. P. Karmann, A. Brand, Moving object recognition using an adaptive background memory[J]. Time Varying Image Processing and Moving Object Recognition, Vol.2, Elsevier, Amsterdam, The Netherlands, 1990.
[25] C. Stauoer, W. Grimson. Adaptive background mixture models for real-time tracking[J]. Proceedings of the IEEE CS Conference on Computer Vision and Pattern Recognition Vol.2, 1999, PP.246-252.
[26] Verri A, Urass, DeMieheliE. Motion Segmentation from optical flow[C],In:Proc the 5th Alvey Vision Conference, Brighton, UK,1989:209-214.
[27] Barron. J, Fleet. D, Beauehemins. Performance of optical flow techniques[J]. International journal of computer vision, 1994:12(1):42-77.
[28]张玲.视频目标跟踪方法研究[D] .中国科学技术大学博士学位论文,2009.
[29] Haritaoglu. L, Harwood. D, and Davis. L. Real-time surveillance of people and their activities[C]. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(8):809-830.
[30] Kilger M. A shadow handler in a video-based real-time traffic monitoring system[C]. IEEE Proc on Application of Computer Vision. Palm Springs, CA, 1992: 11-18.
[31] Michael harville, Hewlet-Packard Laboratories. A Framework for High-Level Feedback to Adaptive, Per-Pixel, Mixture-of-Gaussian Models[C]. In the 7th European Conference on Computer Vision, May28-31, 2002.
[32] C.R. Wren, A. Azarbayejani, T. Darrell, A. P. Pentland. Real-Time Tracking of the Human Body[J]. IEEE Trans. Pattern Analysis and Machine Intelligence,vol.19,no.7, PP.780-785, July 1997.
[33] Stauffer C, Grimson W. Adaptive background mixture models for real-time tracking[C]. Computer Vision and Pattern Recognition, 1999.IEEE Society Conference, 1992(2):246-252.
[34] Chris Stauffer, W.Eric L.Grimson. Learning Patterns of Activity Using Real-Time Tracking[J]. IEEE Transaction on Pattern and Machine Intelligence, 2000-08, 22(8):747-757.
[35] Z.Zivkovic. Improved Adaptive Gaussian Mixture Model for Background Subtraction[C]. Proe. Int’1Conf. Pattern Recognition,vol.2, PP.28-31, 2004.
[36] Elgammal A., Duraisw ami, R. Harwood. D., DavisL.S. Background and foreground modeling using nonparametric kernel density estimation for visualsurveillance[C] Proceedings of IEEE 90(7), July 2002 Page(s):1151-1163.
[37] K. Toyama, J.Krumm, B.Brumitt, and B. Meyers. Principles and Practice of Background Maintenance[C]. proc. IEEEInt’1Conf. Computer Vision, vol.1, PP.255-261, 1999.
[38] A.Monnet,A.Mittal,N.Paragios, and R.Visvanathan. Background Modeling and Subtraction of Dynamic Scenes[C]. Proe. IEEE Int’1 Conf. Computer Vision, vol.2, PP. 1305-1312, 2003.
[39] J. Kato, T. Watanabe, S.Joga,J. Rittseher, and A. Blake. An HMM-Based Segmentation Method for Traffic Monitoring Movies[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, vol.24,no.9,pp.1291-1296.Sept.2002.
[40] M. Mason and Z. Durie. Using Histograms to Deteet and Track Objects in Color Video[J] . Proc. Applied Imagery Pattern Recognition Workshop, PP.154-159,2001.
[41] Heikkila. M., Pietikainen. M. A texture-based method for modeling the background and detecting moving objects[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on Vol.28, Issue4, April 2006 Page(s):657-662.
[42] R. T. Collins, A. J. Lipton, T. Kanade. A System for Video Surveillance and Monitoring [C]. Proc. of American Nuclear Society 8th Int. Topical Meeting on Robotics and Remote Systems, Pittsburgh, PA, Apr.25-29, 1999.
[43] B. Ugur Toin, Yigithan Dedeoglu, A. Enis Cetin, et al. Computer Vision Based Method for Real-time Fire and Flame Detection. Pattern Recognition Letters 27, pp.49–58, 2006.
[44]周平,姚庆杏,钟取发等.基于视频的早期烟雾检测[J].光电工程,Vol.35,No.12 Dec,2008.82-88.
[45]林学阎,王宏等译.计算机视觉——一种现代方法,2004(6):83-111,326-332.
[46]杨静,陈昭炯.不同颜色空间中全局色彩传递算法的分析研究[J].计算机工程与应用, 2007,43(25):80-82.
[47] C.A. Poynton, A Technical Introduction to Digital Video [M], Wiley, New York, 1996.
[48]郝琳波.基于肤色与脸部特征提取的人脸检测.西安电子科技大学硕士学位论文,2008.
[49] Horng Wen-Bing, Peng Jian-Wen, Chen Chih-Yuan. A new image-based real-time flame detection method using color analysis[C]. Proceedings of the 2005 IEEE international Conference on Networking, Sensing and Control. Tucson, Arizona, USA:IEEE Press,2005:100-105.
[50] Chen Thou-Ho, Wu Ping-Hsueh, Chiou Yung-Chuen. An early fire-detection method based on image processing[C]. Proceedings of the 2004 International Conference on Image Processing, Singapore, IEEE Press, 2004:1707-1710.
[51]袁非牛.基于运动累积量和半透明的视频烟雾探测模型[J].数据采集与处理,2007.22(4):396-400.
[52]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.
[53] Feiniu Yuan. A fast accumulative motion orientation model based on integral image for video smoke detection[J]. Pattern Recognition Letters 29 (2008) :925-932.
[54]贾云得.机器视觉[M] .科学出版社,2002.
[55] M.Ghanbari. The cross-search algorithm for motion estimation, IEEE Trans.On Communication, 1990, 38:950-953.
[56] Koga T, Linuma K, Hirano A, et al. Motion compensated interframe coding for video conferencing[A]. In: Proceedings of National Tele2 communications Conference [ C ] , New Orleans, LA, 1981: G51311-G51315.
[57] Zeng R, Liou M L. A new three-step search algorithm for block motion estimation[J]. IEEE Transactions on Circuits System Video Technology, 1994, 4 (8) : 438-442.
[58] Jain J R, Jain A K. Displacement measurement and its application in inter frame image coding [J]. IEEE Transactions on Communications, 1981, 29 (12) : 1799-1808.
[59] Zhu Shan, Ma Kai Kuang. A new diamond search algorithm for fast block matching motion estimation[J]. IEEE Transactions on Image Processing, 2000, 9(2) : 287～290.
[60] Ziyou Xiong, Rodrigo Caballero, Hongcheng Wang et.al. Video-based Smoke Detection: Possibilities, Techniques, and Challenges Suppression and Detection Research and Applications[C]. In: A Technical Conference(SUPDET 2007), Orlando, Florida(March 5-8,2007).
[61]帅师,周平,汪亚明等.基于小波的实时烟雾检测[J].计算机应用研究,2007,24(3):309-311.
[62]吴龙标,连加锐.基于遗传算法的前馈神经网络火灾探测[J].火灾科学,1998,7(2):21-26.
[63]姚伟祥,吴龙标等.火灾探测的一种模糊神经网络方法[J].自然科学进展,1999,9(8):739-745.
[64]乔继斌.基于图像处理技术的火灾检测[D].沈阳工业大学硕士学位论文,2008.
[65]刘亮亮.基于视频监控的火灾图像识别研究[D].华北电力大学(北京)硕士学位论文,2007.
[66]陈祥光,裴旭东.人工神经网络技术及应用[M].中国电力出版社,2003.
[67]吕普铁.基于普通CCD摄像机的火灾探测技术的研究[D] .哈尔滨.哈尔滨工程大学,2003