复杂环境下的人头定位技术研究与实现
|
摘要
智能化监控系统在军事、银行、交通等关键行业的预警,在安全防范和现代化管理中的需求和应用愈加广泛。基于视觉的视频监控系统目前受到各种交通,银行等部门的广泛应用,与其相关的一些技术研究也受到重视。
复杂环境下的人头定位技术研究是基于目前视频图像大量监视数据的自动化分析及有效数据提取问题。目前视频图像的检测技术越来越受到重视,在人体侧立或部分被遮挡,摄像头角度倾斜或俯视下的拍摄等情况下很难获取完整的人脸信息来完成人脸识别和定位。本文采用人头定位的方法能够避免在人脸信息不全时丢失目标。
本文在研究序列图像中动目标检测的基础上结合肤色和结构特征进行了人头的定位。重点分析了常用背景生成方法的优缺点,并采用一种基于stauffer多高斯分布背景模型改进的方法来生成背景图像;利用当前图像与背景图像的差图像来提取运动目标并对提取到的运动目标进行去处干扰的处理;最后利用人头的形状特征采用Hough变换圆环人头定位的算法来完成人头定位;针对人脸不全的情况,论文还分析和实现了基于快速检测的人脸区域定位方法,并对非人脸区域的干扰去除进行研究。
Intelligent monitoring system in the military, banking, transportation and other key sectors of the warning, security and modernization in the management of the needs and applications become more widespread. Vision-based video surveillance system is currently being widely used in traffic, bank and so on, the technology associated with it is paid more attention.
Human head location technology research under complex environment is based on the current video images of the large number of surveillance data analysis and effective automated data extraction problems. At present video images of detection technology is receiving increasing attention, Sometimes the human body or part of it was obscured, the camera angle tilt or overlooking , in those situation we can not access to complete information to complete the face recognition and positioning. In this paper, we use human head location method to incomplete information when people face the loss goals.
This paper investigates the moving objects on the base of the sequence of images, then locate human head with color and structural characteristic. Analyze the advantages and disadvantages of background generation algorithms technique, then presents a new group-update background generation algorithm and an improved multiple Gaussian model background generation algorithm. Using the current image and background images to extract moving target and then eliminate interference from the detected target. In the end, this paper use cirque-based Hough transform to locate human head by head shape features. When we meet the situation that the face is incomplete, this paper also analysis and achieve a human head location method based on the rapid detection.
复杂环境下的人头定位技术研究是基于目前视频图像大量监视数据的自动化分析及有效数据提取问题。目前视频图像的检测技术越来越受到重视,在人体侧立或部分被遮挡,摄像头角度倾斜或俯视下的拍摄等情况下很难获取完整的人脸信息来完成人脸识别和定位。本文采用人头定位的方法能够避免在人脸信息不全时丢失目标。
本文在研究序列图像中动目标检测的基础上结合肤色和结构特征进行了人头的定位。重点分析了常用背景生成方法的优缺点,并采用一种基于stauffer多高斯分布背景模型改进的方法来生成背景图像;利用当前图像与背景图像的差图像来提取运动目标并对提取到的运动目标进行去处干扰的处理;最后利用人头的形状特征采用Hough变换圆环人头定位的算法来完成人头定位;针对人脸不全的情况,论文还分析和实现了基于快速检测的人脸区域定位方法,并对非人脸区域的干扰去除进行研究。
Intelligent monitoring system in the military, banking, transportation and other key sectors of the warning, security and modernization in the management of the needs and applications become more widespread. Vision-based video surveillance system is currently being widely used in traffic, bank and so on, the technology associated with it is paid more attention.
Human head location technology research under complex environment is based on the current video images of the large number of surveillance data analysis and effective automated data extraction problems. At present video images of detection technology is receiving increasing attention, Sometimes the human body or part of it was obscured, the camera angle tilt or overlooking , in those situation we can not access to complete information to complete the face recognition and positioning. In this paper, we use human head location method to incomplete information when people face the loss goals.
This paper investigates the moving objects on the base of the sequence of images, then locate human head with color and structural characteristic. Analyze the advantages and disadvantages of background generation algorithms technique, then presents a new group-update background generation algorithm and an improved multiple Gaussian model background generation algorithm. Using the current image and background images to extract moving target and then eliminate interference from the detected target. In the end, this paper use cirque-based Hough transform to locate human head by head shape features. When we meet the situation that the face is incomplete, this paper also analysis and achieve a human head location method based on the rapid detection.
引文
[1]Stan Birchfield."Ellipitical head tracking using intensity gradients and histograms." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,pages 232-237,June 1998
[2]Mckenna S J.Gong S.Raja Y."Modelling Facial Colour and identity with Gaussian Mistures"[J]Pattern Recogintion,1998
[3]李和恒,张星明.“基于小波神经网络的头部检测技术”华南理工大学计算机科学与技术,广州
[4]周小高,朱秋煜,俞人杰,朱繁源.基于差值图像及肤色特征的人脸定位方法.上海大学学报,2003,9(1):5-8
[5]林洪文,张小虎.基于序列图像的运动目标实时检测方法.光学技术.2004,30(2):215-222
[6]Antonio C,Ricardo L,Huang T S.3D model-based head tracking.Proc.IEEE on ICIP.Kobe,Japan,1999,657-661
[7]Stauffer C,Grimson W E L.Adaptive background mixture models for real-time tracking.Computer Vision and Pattern Recognition,IEEE Computer Society Conference on,1999,2:252
[8]Vieren C,Cabestaing F,Postaire J.Catching Moving Objects with Snakes for Motion Tracking.Pattern Recognition Letters,1995,16:679-685
[9]邵明明.基于头颈部凹点的人头定位新方法.光电子技术.2005,25(2):100-103
[10]Son Lam Phung,A.Bouzerdoum,D.Chai.A novel skin color model in YCbCr color space and its application to human face detection.Proceedings of International Conference on Image Processing,2002,11:289-292.
[11]J-C.Terrillon,M.N.Shirazi,H.Fukamachi etc,Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images.Proceedings of Fourth IEEE International Conference on Automatic Face and Gesture Recognition,2000,54-63.
[12]Rein-Lien Hsu,Mohamed Abdel-Mottaleb,Anil K.Jain.Face.detection in color images.IEEE transactions on pattem analysis and machine intelligence,2002,24:696-706.
[13]杜奇,向健勇,袁胜春.一种改进的最大类问方差法.红外技术,2003,25(5):33-36
[14]Yiwu Lei,Kok Cheong Wong.Ellipse detection based on symmetry.Pattern Recognition Letters,1999,(20):41-47
[15]Christian Daul,Pierre Graebling,Ernest Hirsch.From the Hough Transform to a New Approach for the Detection and Approximation of Elliptical Arcs.Computer Vision and Image understanding,1998,72(3):215-236
[16]M M Jones,J M Rehg.Statistical color models with application to skin detection.Int'l Journal of Computer Vision,2002,46(1)1525-1536
[17]李全民,张运楚.自适应混合高斯背景模型的改进.计算机应用,2007,27(8):2014-2017
[18]陈祖爵,陈潇君,何鸿.基于改进的混合高斯模型的运动目标检测.中国图像图形学报,2007,12(9):1587-1589
[19]吴金勇,葛广英,马国强,徐健健.基于背景自适应生成的监控图像运动目标分割.计算机应用与软件,2007,24(9):51-53
[20]张洪明,赵德斌,高文.基于肤色模型神经网络和人脸结构模型的平面旋转人脸检测.计算机学报,2002,25(11):1250-1256
[21]Yang M H,Kriegman D,Ahuja N.Detecting faces in images..A survey.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(1):34-58
[22]Antonio C,Brendan F,Huang T S.Detection and racking of faces and facial features.IEEE on ICIP,1999:657-661
[23]Vieren C,Cabestasing F,Postaie J.Catching Moving Objects with Snake for Motion Tracking.Patten Recognition Letters,1995,16:679-685
[24]潘志庚,邹鹏程,梁荣华.基于特征人脸和肤色统计的人脸检测.系统仿真学报,2004,16(6):1346-1349
[25]Wysecki G,Stiles W.Color Science:Concepts and Methods,Quantitative Data and Formulae.New York:John Wiley & Sons,2000,165-168
[26]Manjunath B,Ohm J,Vasudevan V,Yamada A.Color and texture descriptors.IEEE Transactions on Circuits and Systems for Video Technology,2001,11(6):703-715
[27]姚鸿勋,刘明宝,高文.基于彩色图像的色系坐标变换的面部定位于跟踪法.计算机学报,2000,23(2):158-165
[28]Lievin M,Luthon F.Nonlinear color space and spatiotemporal mf for hierarchical segmentation of face features in video.IEEE Transactions on Image Processing,2004,13(1):63-65
[29]Gevers T,Semeulders A.Color-based object recognition.Pattern Recognition,1999,32(3):453-464
[30]游亚平,李明,袁保宗.可变光照下的人脸检测.信号处理,2004,20(2):101-107
[31]Yang J,Tsechpenakis G,Metaxas D.Blob analysis of the head and hands:A method for deception.In:Proceedings of 38~(th)Annual Hawaii International Conference on System Science,Hawaii,2005,1(1):20
[32]Yao H,Gao W.Face detection based on skin chrominance and lip chrominance transformation from color and motion information.Pattern Recognition and Artificial Intelligence,2001,34(8):1555-1564
[33]Chai D,Ngan K.Locating facial region of a head-and-shoulders color imae.In:Proceedings of the 3~(rd)International Conference on Automatic Face and Gesture Recognition,Nara,Japan,1998,124-129
[34]雷明,张军英,董济扬.一种可变光照条件下的肤色检测算法.计算机工程与与应用,2002,38(24):123-125
[35]Hsu R.L,Abdel Mottaleb M,Jain A.Face detection in color images.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):696-706
[36]陈锻生,刘政凯.彩色图像人脸高光区域的自动检测与校正方法.软件学报,2004,16(6):1346-1349
[37]Caetano T,Barone D.A probabilistic model for the human skin color.In:Proceedings of the 6~(th)IEEE International Conference on Automatic Face and Gesture Recognition,2004,37-42
[38]Lee J.Y,Yoo S.I,An elliptical boundary model for skin color detection.In:Proceedings of the 2002 International Conference on Imaging Science,Systems and Technology,2002,579-584
[39]Yang M.H,Ahuja N.Gaussian mixture model for human skin color and its application in iamge and video database.In:SPIE 99,1999,3656:458-466
[40]Crowley J,Berard F.Multi-modal tracking of faces for video communications.In:Proceedings of IEEE Conference Computer Vision and Pattern Recognition,Puerto Rico,1997,640-645
[41]Duda R.O,Hart P.E,Stork D.G.Pattern Classification.2rd Edition.New York:John Wiley and Sons,2001
[42]Kruppa H,Bauer M,Shiele.Skin patch detection in real-world images.In:Proceedings of Annual Symposium for Patten Recognition of the DAGM 2002,Lecture Notes in Computer Science 2449,Springer,2002,109-117
[43]艾海舟,武勃等译.图像处理、分析与机器视觉(第二版)[M].北京:人民邮电出版社,2003
[2]Mckenna S J.Gong S.Raja Y."Modelling Facial Colour and identity with Gaussian Mistures"[J]Pattern Recogintion,1998
[3]李和恒,张星明.“基于小波神经网络的头部检测技术”华南理工大学计算机科学与技术,广州
[4]周小高,朱秋煜,俞人杰,朱繁源.基于差值图像及肤色特征的人脸定位方法.上海大学学报,2003,9(1):5-8
[5]林洪文,张小虎.基于序列图像的运动目标实时检测方法.光学技术.2004,30(2):215-222
[6]Antonio C,Ricardo L,Huang T S.3D model-based head tracking.Proc.IEEE on ICIP.Kobe,Japan,1999,657-661
[7]Stauffer C,Grimson W E L.Adaptive background mixture models for real-time tracking.Computer Vision and Pattern Recognition,IEEE Computer Society Conference on,1999,2:252
[8]Vieren C,Cabestaing F,Postaire J.Catching Moving Objects with Snakes for Motion Tracking.Pattern Recognition Letters,1995,16:679-685
[9]邵明明.基于头颈部凹点的人头定位新方法.光电子技术.2005,25(2):100-103
[10]Son Lam Phung,A.Bouzerdoum,D.Chai.A novel skin color model in YCbCr color space and its application to human face detection.Proceedings of International Conference on Image Processing,2002,11:289-292.
[11]J-C.Terrillon,M.N.Shirazi,H.Fukamachi etc,Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images.Proceedings of Fourth IEEE International Conference on Automatic Face and Gesture Recognition,2000,54-63.
[12]Rein-Lien Hsu,Mohamed Abdel-Mottaleb,Anil K.Jain.Face.detection in color images.IEEE transactions on pattem analysis and machine intelligence,2002,24:696-706.
[13]杜奇,向健勇,袁胜春.一种改进的最大类问方差法.红外技术,2003,25(5):33-36
[14]Yiwu Lei,Kok Cheong Wong.Ellipse detection based on symmetry.Pattern Recognition Letters,1999,(20):41-47
[15]Christian Daul,Pierre Graebling,Ernest Hirsch.From the Hough Transform to a New Approach for the Detection and Approximation of Elliptical Arcs.Computer Vision and Image understanding,1998,72(3):215-236
[16]M M Jones,J M Rehg.Statistical color models with application to skin detection.Int'l Journal of Computer Vision,2002,46(1)1525-1536
[17]李全民,张运楚.自适应混合高斯背景模型的改进.计算机应用,2007,27(8):2014-2017
[18]陈祖爵,陈潇君,何鸿.基于改进的混合高斯模型的运动目标检测.中国图像图形学报,2007,12(9):1587-1589
[19]吴金勇,葛广英,马国强,徐健健.基于背景自适应生成的监控图像运动目标分割.计算机应用与软件,2007,24(9):51-53
[20]张洪明,赵德斌,高文.基于肤色模型神经网络和人脸结构模型的平面旋转人脸检测.计算机学报,2002,25(11):1250-1256
[21]Yang M H,Kriegman D,Ahuja N.Detecting faces in images..A survey.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(1):34-58
[22]Antonio C,Brendan F,Huang T S.Detection and racking of faces and facial features.IEEE on ICIP,1999:657-661
[23]Vieren C,Cabestasing F,Postaie J.Catching Moving Objects with Snake for Motion Tracking.Patten Recognition Letters,1995,16:679-685
[24]潘志庚,邹鹏程,梁荣华.基于特征人脸和肤色统计的人脸检测.系统仿真学报,2004,16(6):1346-1349
[25]Wysecki G,Stiles W.Color Science:Concepts and Methods,Quantitative Data and Formulae.New York:John Wiley & Sons,2000,165-168
[26]Manjunath B,Ohm J,Vasudevan V,Yamada A.Color and texture descriptors.IEEE Transactions on Circuits and Systems for Video Technology,2001,11(6):703-715
[27]姚鸿勋,刘明宝,高文.基于彩色图像的色系坐标变换的面部定位于跟踪法.计算机学报,2000,23(2):158-165
[28]Lievin M,Luthon F.Nonlinear color space and spatiotemporal mf for hierarchical segmentation of face features in video.IEEE Transactions on Image Processing,2004,13(1):63-65
[29]Gevers T,Semeulders A.Color-based object recognition.Pattern Recognition,1999,32(3):453-464
[30]游亚平,李明,袁保宗.可变光照下的人脸检测.信号处理,2004,20(2):101-107
[31]Yang J,Tsechpenakis G,Metaxas D.Blob analysis of the head and hands:A method for deception.In:Proceedings of 38~(th)Annual Hawaii International Conference on System Science,Hawaii,2005,1(1):20
[32]Yao H,Gao W.Face detection based on skin chrominance and lip chrominance transformation from color and motion information.Pattern Recognition and Artificial Intelligence,2001,34(8):1555-1564
[33]Chai D,Ngan K.Locating facial region of a head-and-shoulders color imae.In:Proceedings of the 3~(rd)International Conference on Automatic Face and Gesture Recognition,Nara,Japan,1998,124-129
[34]雷明,张军英,董济扬.一种可变光照条件下的肤色检测算法.计算机工程与与应用,2002,38(24):123-125
[35]Hsu R.L,Abdel Mottaleb M,Jain A.Face detection in color images.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):696-706
[36]陈锻生,刘政凯.彩色图像人脸高光区域的自动检测与校正方法.软件学报,2004,16(6):1346-1349
[37]Caetano T,Barone D.A probabilistic model for the human skin color.In:Proceedings of the 6~(th)IEEE International Conference on Automatic Face and Gesture Recognition,2004,37-42
[38]Lee J.Y,Yoo S.I,An elliptical boundary model for skin color detection.In:Proceedings of the 2002 International Conference on Imaging Science,Systems and Technology,2002,579-584
[39]Yang M.H,Ahuja N.Gaussian mixture model for human skin color and its application in iamge and video database.In:SPIE 99,1999,3656:458-466
[40]Crowley J,Berard F.Multi-modal tracking of faces for video communications.In:Proceedings of IEEE Conference Computer Vision and Pattern Recognition,Puerto Rico,1997,640-645
[41]Duda R.O,Hart P.E,Stork D.G.Pattern Classification.2rd Edition.New York:John Wiley and Sons,2001
[42]Kruppa H,Bauer M,Shiele.Skin patch detection in real-world images.In:Proceedings of Annual Symposium for Patten Recognition of the DAGM 2002,Lecture Notes in Computer Science 2449,Springer,2002,109-117
[43]艾海舟,武勃等译.图像处理、分析与机器视觉(第二版)[M].北京:人民邮电出版社,2003