动态场景监控系统中人数统计算法的研究
|
摘要
当前社会是一个高速发展的社会。经济在不断的发展,硬件水平也在不断提高。随着人们生活现代化程度的提高,视频监控系统的应用也变得无处不在。利用计算机图像处理技术提高视频监控系统的自动化程度,尽量减少人工作业,将是视频监控系统未来的发展方向。特别是在各种公共场所中,人群的流动越来越频繁。如何对公共场所中的人群有效的管理和控制,是当前需要解决的一个关键问题。由此,动态场景下的人数统计方法就应运而生。
本文介绍了目标检测与跟踪技术的现状,研究了主要检测、跟踪算法的基本理论,分析了当前主要算法的优缺点。在此基础上构建了一个人物分割与人群跟踪相结合的人物计数系统,在计算速度与稳定性方面较已存在系统有了较大提高。系统主要包括四个部分：目标检测、粗略分割、单人计数、人群计数。首先对监控区域运动目标检测提取并滤除噪声,将背景区域中被认定为人群的区域分割并标注,然后分别对人群和单人跟踪计数,最后将数据相加得到具体人数。
在目标检测中,针对提取效果和实时性方面的要求,本文使用了背景差分与帧间差分相结合的检测算法,使用帧间差分完成背景更新,使用背景差分提取前景。在分割过程中,为了避免遮挡物的影响,采用重叠率代替边框中心点之间距离来比较相似度。在人群跟踪步骤中,使用面积统计法,对人物的数量进行粗略统计,并利用融合与分裂检测,补偿第一次分割时产生遮挡所造成的误差。在人群统计过程中,依据相关性进一步补偿了由于人物分割导致的误判。
实验证明,本文构建的视频监控系统,可以对进入监控范围内的人物进行数量统计,并在提高实时性的同时也兼顾了统计的准确率。
At present society is a rapidly developing society. Along with economical development, progress of the hardware is also constantly. With the modernization of people's lives, the application of video surveillance systems has become ubiquitous. The future of video surveillance system development focus on enhance the degree of automation and minimizing manual operations, so make full use of computer image processing technology is one of the most important way. In particular, in various public places, the crowd movements become more frequent. How the crowd thoroughly enjoyed themselves in public places, effective management and control, is currently a key issue to be resolved. As a result, the counting of the people in dynamic scenes under the statistical methods came into being.
This article describes the development status of target detection and tracking technology. Study the basic theory of tracking algorithm and main detection, analysis of the advantages and disadvantages of current algorithm. On this basis, combine character segmentation and crowned tracking to build people counting system. Our system has been greatly enhanced at calculation of speed and stability. System mainly includes four components:target detection, a rough segmentation, single count, the crowd count. Firstly, the regional campaign on the monitoring target detection extract and filter out noise, the background regions have been identified as the crowd of region segmentation and annotation, and then separately track the population and single count, the final data to be added to the exact number.
Completion of background updating using the frame difference, foreground extracted using background difference. In the segmentation process, in order to avoid the impact of occlusion, we consider similarity between tracker and measure not only by comparing central positions but also height and width of the bounding box:using overlapping area. The overlapping rate matrix functions as similarity and can reduce computing complexity effectively. Then we used an area of statistics on the number of people to get a rough statistics, and using merging and splitting to compensate weakness of multiple-human segmentation from handle occlusion.
From experiments we can see, this paper builds a real-time, effective monitoring system that can monitor the right to enter characters within the scope of quantitative statistics. Using the Coarse-to-fine segmentation, instead of overlapping frame rate to compare the distance between the centers of similarity, reducing the computational complexity; in the population statistics of the time, according to the relevance of compensation due to character segmentation result of misjudgment. Experiments show that the system in improving the real-time, while also taking into accounts its accuracy.
本文介绍了目标检测与跟踪技术的现状,研究了主要检测、跟踪算法的基本理论,分析了当前主要算法的优缺点。在此基础上构建了一个人物分割与人群跟踪相结合的人物计数系统,在计算速度与稳定性方面较已存在系统有了较大提高。系统主要包括四个部分：目标检测、粗略分割、单人计数、人群计数。首先对监控区域运动目标检测提取并滤除噪声,将背景区域中被认定为人群的区域分割并标注,然后分别对人群和单人跟踪计数,最后将数据相加得到具体人数。
在目标检测中,针对提取效果和实时性方面的要求,本文使用了背景差分与帧间差分相结合的检测算法,使用帧间差分完成背景更新,使用背景差分提取前景。在分割过程中,为了避免遮挡物的影响,采用重叠率代替边框中心点之间距离来比较相似度。在人群跟踪步骤中,使用面积统计法,对人物的数量进行粗略统计,并利用融合与分裂检测,补偿第一次分割时产生遮挡所造成的误差。在人群统计过程中,依据相关性进一步补偿了由于人物分割导致的误判。
实验证明,本文构建的视频监控系统,可以对进入监控范围内的人物进行数量统计,并在提高实时性的同时也兼顾了统计的准确率。
At present society is a rapidly developing society. Along with economical development, progress of the hardware is also constantly. With the modernization of people's lives, the application of video surveillance systems has become ubiquitous. The future of video surveillance system development focus on enhance the degree of automation and minimizing manual operations, so make full use of computer image processing technology is one of the most important way. In particular, in various public places, the crowd movements become more frequent. How the crowd thoroughly enjoyed themselves in public places, effective management and control, is currently a key issue to be resolved. As a result, the counting of the people in dynamic scenes under the statistical methods came into being.
This article describes the development status of target detection and tracking technology. Study the basic theory of tracking algorithm and main detection, analysis of the advantages and disadvantages of current algorithm. On this basis, combine character segmentation and crowned tracking to build people counting system. Our system has been greatly enhanced at calculation of speed and stability. System mainly includes four components:target detection, a rough segmentation, single count, the crowd count. Firstly, the regional campaign on the monitoring target detection extract and filter out noise, the background regions have been identified as the crowd of region segmentation and annotation, and then separately track the population and single count, the final data to be added to the exact number.
Completion of background updating using the frame difference, foreground extracted using background difference. In the segmentation process, in order to avoid the impact of occlusion, we consider similarity between tracker and measure not only by comparing central positions but also height and width of the bounding box:using overlapping area. The overlapping rate matrix functions as similarity and can reduce computing complexity effectively. Then we used an area of statistics on the number of people to get a rough statistics, and using merging and splitting to compensate weakness of multiple-human segmentation from handle occlusion.
From experiments we can see, this paper builds a real-time, effective monitoring system that can monitor the right to enter characters within the scope of quantitative statistics. Using the Coarse-to-fine segmentation, instead of overlapping frame rate to compare the distance between the centers of similarity, reducing the computational complexity; in the population statistics of the time, according to the relevance of compensation due to character segmentation result of misjudgment. Experiments show that the system in improving the real-time, while also taking into accounts its accuracy.
引文
[1]Weizhong ye, Yangsheng Xu, Zhi Zhong."Robust people counting in crowded environment" Proceedings of the 2007 IEEE International Conference on Robotics and Biomimetics December 15-18,2007,Sanya,China..
[2]Xiaowei Xu, Zhiyan Wang, Yinghong Liang,Yanqing Zhang. "A rapid method for passing people counting in monocular video sequences”Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, Hong Kong,19-22 August 2007
[3]V.Rabaud and S.Belongie,"Countingcrowdedmoving objects," IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2006, vol.1,pp.705-711,June2006.
[4]Rafacel C.Gonzalez,Richard E.Woods.冈萨雷斯数字图像处理(第二版),电子工业出版社。2005
[5]贾永红.数字图像处理.武汉大学出版社.2003.9
[6]陈天华.数字图像处理[M].北京：清华大学出版社.2007.
[7]王树文.数学形态学在图像处理中的应用[J].计算机工程与应用.2004,40(32)：89-92.
[8]Lee J S J, Haralick R M. Morphology edge detection [J].IEEE Trans, on Robotics Antomat.1987 (3):140-156.
[9]Salembier P., Brigger P., Casas J.R.,et al. Morphological operators for image and video compression[J].IEEE Trans.Image Processing.1996,5(6):881-898.
[10]William K Part.数字图像处理,邓鲁华译.北京：机械工业出版社,2005
[11]蓝章礼,李益才,李艾星.数字图像处理与图像通信[M].北京：清华大学出版社.2009.
[12]阮秋琦等编著.数字图像处理学(第二版).北京：电子工业出版社,2007.
[13]谢凤英.Visual C++数字图像处理.电子工业出版.社发行部.2008
[14]Kenneth R Castleman.数字图像处理,朱志刚译.北京：电子工业出版社,2002
[15]章毓晋.图像处理和分析技术[M].北京：高等教育出版社.2008.
[16]边肇祺等,模式识别.清华大学出版社,1988.
[17]OtSu N.A threshold selection method from gray level histograms.IEEE Trans on Syst Man Cybernet,1979,9 (1):62-66.
[18]inku Acharya Ajoy K.Ray.田浩 葛秀慧 王顶 等译 数字图像处理原理与应用.清华大学出版社.2007
[19]王新成.高级图像处理技术.中国科学技术出版社.2000
[20]夏德深.计算机图像处理及应用.东南大学出版社.2005
[21]L Haritaoglu,D Harwood,L S Davis.W4:Rea-Time Surveillance of People and Their Activities.IEEE Trans.PAMI,2000,22(8):80.830
[22]A.Elgammal,IL Duraiswaafi,D.Harwood,et al.Background and foreground modeling using nonparametric kernel density estimation for visual surveillance.Proc.Of the IEEE,2002,v01.90:1151.1163.
[23]P.Msssirao.Background subtraction techniques:a review.2004 IEEE International Conference on Systems,Man and Cybernetics,2004,3099-3104.
[24]张玲,叶海炳,何伟.一种基于边缘信息的改进车辆检测方法.重庆大学学报(自然科学版),2004,27(11)：56.58.
[25]王建中,姜礼明.基于块匹配的运动对像检测方法.微电子信息,2005,22(1)：204.204.
[26]朱江,宣国容.基于视频动态投影的实时车辆流量检测系统.计算机工程,2001,27(11)：25.26.
[27]Kilger M.A shadow handler in a video-based real-time traffic monitoring system In:Proc IEEE workshop on Applications of Computer Vision,Palm Springs,C A.1992,1060-1066.
[28]Stauffer C and Grimson W.Adaptive background mixture models for real-time tracking.In:Proc IEEE Conference on Computer Vision and Pattern Recognition,Fort Collins,Colorado,1999,2:246-252.
[29]Mittal A,Huttenlocher D.Scene modeling for wide area surveillance and image synthesis[A]. In:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition[C],Hilton Head Island,SC,USA,2000:160～16
[30]Wren C, AzabayejaniA, Darrel T'et al. Pfinder:Real2ti me tracking of the human body[J]. IEEE Transactions on Pattem Analysis and Machine Intelligence,1 997,19(7):780-785.
[31]K.Toyama, J.Krumm, B.Brumitt, andB.Meyers, "Wallflower:Principles and Practice of Background Maintenance,"Inter.Conf. On Computer Vision, Corfu, Greece,1999:255-261
[32]Lipton A,Fujiyoshi H,Moving target classification and tracking from real-time video[A].In:proceedings of IEEE Workshop on Applications of Computer Vision[C],Princeton,NJ,USA,1998:8-14.
[33]Ai Hai-zhou,Lv Feng-jun.Changes detection and segmentation in visual surveillance[J].Computer Engineering and Application,2000,37(5):75-77.
[34]贾云得,机器视觉,科学出版社,2000
[35]A.M.Tekalp,"Digital Video Processing".Prentice Hall,1995.
[36]Horn BK, Schunk BG Determining optical flow.Artificial Intelligence,1981,17(1-3):185-203
[37]张娟,基于单目视觉运动背景下的动目标检测有关问题的研究,西北大学,2009
[38]杨文凯.序列图像中运动目标的检测[D].硕士学位论文,2004.
[39]TH Chen and CW Hsu,"Anautomatic bi-directional passing-people counting method based on color-image processing",37 TH IEEE(2003)International Carnahan Conference on Security Technology,pp.200-207,2003.
[40]L.Snidaro, C.Micheloni, C.Chiavedale,"Video security for ambient intelligence", IEEE Trans.System, Man, and Cybernetics Part A, vol.35, pp.133-144,2005.
[41]L.Marcenaro, L.Marchesotti and C.S.Regazzoni," Tracking and counting multiple interacting people in indoor scenes", Proceedings 3rd IEEE Int.Workshop on PETS, pp.56-61,2002.
[42]Sebastien Harasse, Laurent Bonnaud, Michel Desvignes,"Finding people in video streams by statistical modeling", ICAPR (2), pp.608-617,2005
[43]Christof Ridder,01af Munkelt,and Harald Ki chner, "Adaptive Background Estimation and Foreground Detection using Kalman Filtering", Proceedings of International Conference on recent Advances in Mechatronics. ICR A M'95 UNESCO Chair on Mechatronics. pages 193～109.1995
[44]D.Kolle.J.Weber,T.Huang，J.Malik,G.Ogasawara.B.Rao,and.Russel. "Towards robust automatic traffic scene analysis in real time".In Proc.of the International Conference on Pattern Recognition,Israel.November 1994
[45]Wren,C.R.et al,"Pfinder:Real-Time Tracking of the Human Body."in IEEE Transactions on Pattern Analysis and Machine Intelligence 1997.19(7),pages 780-785
[46]N.Friedman and S.Russell,"Image segmentation in video sequence:A probabilistic approach,"in Proc.of the Thirteenth Conference on Uncertainty in Artificial Intelligence(uAI),1997
[47]C.Stauffer.and W.E.L Grimson."Adaptive Background Mixture Models for Real-Time Tracking",IEEE Conf.on CVPR.1999
[48]N.Amamoto and K.Matsumoto."Obstruction detector by environmental adaptive background image updating",4th World Congress on intelligent Transport Systems,number 4,pages 1-7,Berlin.Oct.1997
[49]马颂德,唐明.非参数化区域竞争方法：一种新的图像分割框架[j].自动化学报,2001,27(6)i737—743.
[50]T.Zhao and R.Nevatia,"Tracking multiple humansin complex situations", IEEE Trans.Pattern Anal.Mach.Intell.,Vol.26,pp.1208-1221,2004.
[51]Haritaoglul,HarwoodD,DavisLS,"W4:Real-times urveillance of people and their activities", IEEE Trans.Pattern Anal.Mach.Intell.,vol.22,pp.809-830,2000.
[52]TaoYang, StanZ.Li, QuanPan, JingLi, Real-time multiple objects tracking with occlusion handling in dynamicscenes",In CVPR05I(2005),pp.970-975,2005.
[2]Xiaowei Xu, Zhiyan Wang, Yinghong Liang,Yanqing Zhang. "A rapid method for passing people counting in monocular video sequences”Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, Hong Kong,19-22 August 2007
[3]V.Rabaud and S.Belongie,"Countingcrowdedmoving objects," IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2006, vol.1,pp.705-711,June2006.
[4]Rafacel C.Gonzalez,Richard E.Woods.冈萨雷斯数字图像处理(第二版),电子工业出版社。2005
[5]贾永红.数字图像处理.武汉大学出版社.2003.9
[6]陈天华.数字图像处理[M].北京：清华大学出版社.2007.
[7]王树文.数学形态学在图像处理中的应用[J].计算机工程与应用.2004,40(32)：89-92.
[8]Lee J S J, Haralick R M. Morphology edge detection [J].IEEE Trans, on Robotics Antomat.1987 (3):140-156.
[9]Salembier P., Brigger P., Casas J.R.,et al. Morphological operators for image and video compression[J].IEEE Trans.Image Processing.1996,5(6):881-898.
[10]William K Part.数字图像处理,邓鲁华译.北京：机械工业出版社,2005
[11]蓝章礼,李益才,李艾星.数字图像处理与图像通信[M].北京：清华大学出版社.2009.
[12]阮秋琦等编著.数字图像处理学(第二版).北京：电子工业出版社,2007.
[13]谢凤英.Visual C++数字图像处理.电子工业出版.社发行部.2008
[14]Kenneth R Castleman.数字图像处理,朱志刚译.北京：电子工业出版社,2002
[15]章毓晋.图像处理和分析技术[M].北京：高等教育出版社.2008.
[16]边肇祺等,模式识别.清华大学出版社,1988.
[17]OtSu N.A threshold selection method from gray level histograms.IEEE Trans on Syst Man Cybernet,1979,9 (1):62-66.
[18]inku Acharya Ajoy K.Ray.田浩 葛秀慧 王顶 等译 数字图像处理原理与应用.清华大学出版社.2007
[19]王新成.高级图像处理技术.中国科学技术出版社.2000
[20]夏德深.计算机图像处理及应用.东南大学出版社.2005
[21]L Haritaoglu,D Harwood,L S Davis.W4:Rea-Time Surveillance of People and Their Activities.IEEE Trans.PAMI,2000,22(8):80.830
[22]A.Elgammal,IL Duraiswaafi,D.Harwood,et al.Background and foreground modeling using nonparametric kernel density estimation for visual surveillance.Proc.Of the IEEE,2002,v01.90:1151.1163.
[23]P.Msssirao.Background subtraction techniques:a review.2004 IEEE International Conference on Systems,Man and Cybernetics,2004,3099-3104.
[24]张玲,叶海炳,何伟.一种基于边缘信息的改进车辆检测方法.重庆大学学报(自然科学版),2004,27(11)：56.58.
[25]王建中,姜礼明.基于块匹配的运动对像检测方法.微电子信息,2005,22(1)：204.204.
[26]朱江,宣国容.基于视频动态投影的实时车辆流量检测系统.计算机工程,2001,27(11)：25.26.
[27]Kilger M.A shadow handler in a video-based real-time traffic monitoring system In:Proc IEEE workshop on Applications of Computer Vision,Palm Springs,C A.1992,1060-1066.
[28]Stauffer C and Grimson W.Adaptive background mixture models for real-time tracking.In:Proc IEEE Conference on Computer Vision and Pattern Recognition,Fort Collins,Colorado,1999,2:246-252.
[29]Mittal A,Huttenlocher D.Scene modeling for wide area surveillance and image synthesis[A]. In:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition[C],Hilton Head Island,SC,USA,2000:160～16
[30]Wren C, AzabayejaniA, Darrel T'et al. Pfinder:Real2ti me tracking of the human body[J]. IEEE Transactions on Pattem Analysis and Machine Intelligence,1 997,19(7):780-785.
[31]K.Toyama, J.Krumm, B.Brumitt, andB.Meyers, "Wallflower:Principles and Practice of Background Maintenance,"Inter.Conf. On Computer Vision, Corfu, Greece,1999:255-261
[32]Lipton A,Fujiyoshi H,Moving target classification and tracking from real-time video[A].In:proceedings of IEEE Workshop on Applications of Computer Vision[C],Princeton,NJ,USA,1998:8-14.
[33]Ai Hai-zhou,Lv Feng-jun.Changes detection and segmentation in visual surveillance[J].Computer Engineering and Application,2000,37(5):75-77.
[34]贾云得,机器视觉,科学出版社,2000
[35]A.M.Tekalp,"Digital Video Processing".Prentice Hall,1995.
[36]Horn BK, Schunk BG Determining optical flow.Artificial Intelligence,1981,17(1-3):185-203
[37]张娟,基于单目视觉运动背景下的动目标检测有关问题的研究,西北大学,2009
[38]杨文凯.序列图像中运动目标的检测[D].硕士学位论文,2004.
[39]TH Chen and CW Hsu,"Anautomatic bi-directional passing-people counting method based on color-image processing",37 TH IEEE(2003)International Carnahan Conference on Security Technology,pp.200-207,2003.
[40]L.Snidaro, C.Micheloni, C.Chiavedale,"Video security for ambient intelligence", IEEE Trans.System, Man, and Cybernetics Part A, vol.35, pp.133-144,2005.
[41]L.Marcenaro, L.Marchesotti and C.S.Regazzoni," Tracking and counting multiple interacting people in indoor scenes", Proceedings 3rd IEEE Int.Workshop on PETS, pp.56-61,2002.
[42]Sebastien Harasse, Laurent Bonnaud, Michel Desvignes,"Finding people in video streams by statistical modeling", ICAPR (2), pp.608-617,2005
[43]Christof Ridder,01af Munkelt,and Harald Ki chner, "Adaptive Background Estimation and Foreground Detection using Kalman Filtering", Proceedings of International Conference on recent Advances in Mechatronics. ICR A M'95 UNESCO Chair on Mechatronics. pages 193～109.1995
[44]D.Kolle.J.Weber,T.Huang，J.Malik,G.Ogasawara.B.Rao,and.Russel. "Towards robust automatic traffic scene analysis in real time".In Proc.of the International Conference on Pattern Recognition,Israel.November 1994
[45]Wren,C.R.et al,"Pfinder:Real-Time Tracking of the Human Body."in IEEE Transactions on Pattern Analysis and Machine Intelligence 1997.19(7),pages 780-785
[46]N.Friedman and S.Russell,"Image segmentation in video sequence:A probabilistic approach,"in Proc.of the Thirteenth Conference on Uncertainty in Artificial Intelligence(uAI),1997
[47]C.Stauffer.and W.E.L Grimson."Adaptive Background Mixture Models for Real-Time Tracking",IEEE Conf.on CVPR.1999
[48]N.Amamoto and K.Matsumoto."Obstruction detector by environmental adaptive background image updating",4th World Congress on intelligent Transport Systems,number 4,pages 1-7,Berlin.Oct.1997
[49]马颂德,唐明.非参数化区域竞争方法：一种新的图像分割框架[j].自动化学报,2001,27(6)i737—743.
[50]T.Zhao and R.Nevatia,"Tracking multiple humansin complex situations", IEEE Trans.Pattern Anal.Mach.Intell.,Vol.26,pp.1208-1221,2004.
[51]Haritaoglul,HarwoodD,DavisLS,"W4:Real-times urveillance of people and their activities", IEEE Trans.Pattern Anal.Mach.Intell.,vol.22,pp.809-830,2000.
[52]TaoYang, StanZ.Li, QuanPan, JingLi, Real-time multiple objects tracking with occlusion handling in dynamicscenes",In CVPR05I(2005),pp.970-975,2005.