车辆辅助驾驶系统中基于计算机视觉的行人检测技术研究
|
摘要
行人检测是智能车辆辅助导航系统中的一项关键技术,也是目前计算机应用领域的研究热点之一。它处于智能车辆辅助导航系统的底层,是各种后续高级处理如目标分类、行为理解的基础。行人检测技术在智能控制系统、虚拟现实、机器人应用等方面也将得到广泛地应用。
论文对车辆辅助驾驶系统中基于计算机视觉的行人检测技术进行研究,首先详细分析了基于视频图像的运动目标检测方法,重点研究了减背景法,提出了背景建模方法的改进算法,该算法是借助图像中相邻象素的邻域相关性,只对间隔的象素点建立混合高斯模型,没有建立混合高斯模型的点则利用象素的邻域相关性进行判断;为了克服了减背景法对光照变化敏感的不足,再结合帧差法对运动目标进行检测。其次,对运动目标进行行人识别,根据行人多种简单特征建立行人匹配模板,在图像序列中对检测到的目标进行匹配和识别,实时的分割出准确完整的运动行人。最后,对行人运动跟踪技术进行了研究,实现了一种以运动目标质心模型求得运动目标位置的测量方法,并结合卡尔曼滤波方法对行人的矩形窗口进行预测,建立动态可变的感兴趣区域,缩小了行人的搜索范围。
论文采用手持摄像机的形式来模拟装载在智能车辆上的可变焦距的摄像机,对采集到的视频图像进行处理。本文提出的算法能够实现对车辆前方的行人进行实时有效地检测识别,同时对行人进行跟踪。为了验证算法的有效性,进行了一定量的试验,试验结果表明,该算法可以满足行人检测系统的实时性要求,相对于以往算法也更加准确可靠。
The technique of moving pedestrian detection is one of the key techniques for Intelligent Vehicle Navigation System and is coming to a hot spot of research in computer application field at present. It is in the Intelligent Vehicle assisted navigation technology bottom, splitting the moving objects real-time and effectively is essential foundation for the subsequent processing, including target identification, tracking behavior comprehension. Method of moving pedestrian detection will also be widely used in the intelligent control system, virtual reality, robot applications.
This paper is study on the Computer Vision Based Pedestrian Detection for Driver Assistance Systems. First of all, a detailed analysis of video images based on the moving target detection methods, the dissertation mainly studied the background subtraction, and improved background modeling method, considering the pixels neighboring relativity, the algorithm through the interval pixels establishment of Gaussian mixture model instead of the traditional point by point establishes Gaussian mixture model in background subtraction. In order to overcome the lack of sensitivity of light change, combining the adaptive background subtraction with the symmetrical differencing obtains the integrity foreground image. Then, during the process of matching, the template for pedestrian matching and recognizing in image sequence was presented by fusing several characters of targets. Finally, on the basis of moving pedestrian segmentation in this paper, continue to process the Video images, combined with Kalman filter estimates the position of the pedestrian bounding box, A dynamic and variable area of interest is formed to narrow the seek range of pedestrian .
In the experiments, used hand-held video camera to replace the video camera equipped on the moving vehicle to process the images. The experiment results indicate that the algorithms introduced could achieve effective recognition of the proceeding pedestrians. At the same time, the algorithms have good tracking. A serial of experiment have been implemented to verify the effectiveness of the method supported by the papers, which can satisfied with the requisition of the real time system and have been more precisely.
论文对车辆辅助驾驶系统中基于计算机视觉的行人检测技术进行研究,首先详细分析了基于视频图像的运动目标检测方法,重点研究了减背景法,提出了背景建模方法的改进算法,该算法是借助图像中相邻象素的邻域相关性,只对间隔的象素点建立混合高斯模型,没有建立混合高斯模型的点则利用象素的邻域相关性进行判断;为了克服了减背景法对光照变化敏感的不足,再结合帧差法对运动目标进行检测。其次,对运动目标进行行人识别,根据行人多种简单特征建立行人匹配模板,在图像序列中对检测到的目标进行匹配和识别,实时的分割出准确完整的运动行人。最后,对行人运动跟踪技术进行了研究,实现了一种以运动目标质心模型求得运动目标位置的测量方法,并结合卡尔曼滤波方法对行人的矩形窗口进行预测,建立动态可变的感兴趣区域,缩小了行人的搜索范围。
论文采用手持摄像机的形式来模拟装载在智能车辆上的可变焦距的摄像机,对采集到的视频图像进行处理。本文提出的算法能够实现对车辆前方的行人进行实时有效地检测识别,同时对行人进行跟踪。为了验证算法的有效性,进行了一定量的试验,试验结果表明,该算法可以满足行人检测系统的实时性要求,相对于以往算法也更加准确可靠。
The technique of moving pedestrian detection is one of the key techniques for Intelligent Vehicle Navigation System and is coming to a hot spot of research in computer application field at present. It is in the Intelligent Vehicle assisted navigation technology bottom, splitting the moving objects real-time and effectively is essential foundation for the subsequent processing, including target identification, tracking behavior comprehension. Method of moving pedestrian detection will also be widely used in the intelligent control system, virtual reality, robot applications.
This paper is study on the Computer Vision Based Pedestrian Detection for Driver Assistance Systems. First of all, a detailed analysis of video images based on the moving target detection methods, the dissertation mainly studied the background subtraction, and improved background modeling method, considering the pixels neighboring relativity, the algorithm through the interval pixels establishment of Gaussian mixture model instead of the traditional point by point establishes Gaussian mixture model in background subtraction. In order to overcome the lack of sensitivity of light change, combining the adaptive background subtraction with the symmetrical differencing obtains the integrity foreground image. Then, during the process of matching, the template for pedestrian matching and recognizing in image sequence was presented by fusing several characters of targets. Finally, on the basis of moving pedestrian segmentation in this paper, continue to process the Video images, combined with Kalman filter estimates the position of the pedestrian bounding box, A dynamic and variable area of interest is formed to narrow the seek range of pedestrian .
In the experiments, used hand-held video camera to replace the video camera equipped on the moving vehicle to process the images. The experiment results indicate that the algorithms introduced could achieve effective recognition of the proceeding pedestrians. At the same time, the algorithms have good tracking. A serial of experiment have been implemented to verify the effectiveness of the method supported by the papers, which can satisfied with the requisition of the real time system and have been more precisely.
引文
[1]孙庆杰.静态图像中人体检测技术研究:(博士学位论文).北京:中国科学软件研究所,2004。
[2]王亮,胡卫明,谭铁牛.基于步态的身份识别.计算机学报,2006,26(3):353-360.
[3]Hong Cheng,Nanning Zheng,Junjie Qin.Pedestrian Detection Using Sparse Gabor Filter and Support Vector Machine.Intelligent Vehicles Symposium,USA,2005:583-587.
[4]田广,戚飞虎,朱文佳等。基于移动拍摄下基于人体部位的行人检测.系统仿真学报,2006,18(10):2906-2910.
[5]黄琛.基于Hausdorff距离模板匹配的行人检测算法研究与应用:(硕士学位论文).北京:清华大学,2006.
[6]M Bertozzi,A Broggi,R Chapuis et al.Shape-based Pedestrian Detection and Localization.Intelligent Vehicles Symposium 2003,USA,2003:410-415.
[7]B Heisele,C W ohler.Motion-based Recognition of Pedestrians.Intelligent Conference on Pattern Recognition,August,1998:1325-1330.
[8]Alan J,Lipton- Local Application of Optic flow to Analyze Rigid Versus NonOrigid Motion.Robotics Institute,USA,1999.
[9]V Philomin,R Duraiswami,L Davis.Pedestrian Tracking from a Moving Vehicle.Intelligent Vehicles Symposium,USA,2000:350-355.
[10]O Masoud.Robust Pedestrian Tracking Using a Model Obased Approach.Conference on Intelligent Transportation Systems,USA,1997:338-343.
[11]M Oren,C Papageorgiu,P Sihna et al.Pedestrian Detection using Wavelet Templates.Puerto Rico:Procs,IEConf.On Computer Vision and Pattern Recognition,June 1997:193-199.
[12]A Mohan,C Papageorgiou,T Poggio.Example-based Object Detection in Images by Components.IEEE Trausactiouson Pattern Analysis and Machine Intelligence,2001,23(4):349-361.
[13]A Broggi,A Fascioli,I Fedriga et al.Stereo-Based Preprocessing for Human Shape Localization in Unstructured Envimuments.IEEE Intelligent Vehicles Symposium2003,USA,2003:410-415.
[14]L Zhao,C Thorpe.Stereo and Neural Network-based Pedestrian Detection.IEEE Transaction son Intelligent Transportation Systems,2000,1(3):148-154.
[15]Neri A,Colonnese S,Rusao G et al.Automatic moving object and background separation.Signal Processing,1998,66(2):219-232.
[16]Kamijo S,Sakauchi M.Segmentation of vehicles and pedestrians in traffic scence by spatio-temporal Markov random field model.Multimedia and Expo,USA,2003:285-288.
[17]袁基炜,史忠科.一种图像序列自动分割新方法.计算机工程与应用,2004,29(3):144-148.
[18]Hiroshi Koyasu,Jun MIURA,Yoshiki Shirai.Realtime Omnidirectional Stereo for Obstacle Detection and Tracking in Dynamic Environments.IEEE Trans on Intelligent Transportation Systems,2001,5(6):244-251.
[19]Zhao L,Thorpe C E.Stereo and neural network-based pedestrian detection.IEEE Trans on Intelligent Transportation Systems,2000,1(3):148-154.
[20]STAUFFER C,GRIMSON W E L.Adaptive Background mixture models for real-time tracking.Proc.Conf.Computer Vision and Pattern Recognition,USA,1999:246-252.
[21]GIANLUCA B,MASSIMO B.Background estimation with Gaussian distribution for image segmentation,a fast approach.IEEE International Workshop on Measurement Systems for Homeland Security,Contraband Detection and Personal Safety Orlando,USA,2005:29-30.
[22]贺贵明,李凌娟,贾振堂.一种快速的基于对称差分的视频分割算法.小型微型计算机系统,2003,24(6):966-968.
[23]李刚,邱尚斌,林凌等.基于背景差法和帧间差法的运动目标检测方法.仪器仪表学报,2006。26(8):118-123.
[24]Chu J W,Ji L S,Guo L et al.Study on Method of Detecting Preceding Vehicle Based on Monocular Camera.IEEE Intelligent Vehicles,Pama,Italy,2004:750-755.
[25]Shin KATO,Kohji TOMITA,Sadayuki TSUGAWA.Visual Navigation along Reference Lines and Collision Avoidance for Autonomous Vehicles.IEEE Intelligent Vehicles Symposium,USA,1996:385-390.
[26]Surendra G,Osama M,Robert F et al.Detection and Classification of Vehicles.IEEE Transaction on Intelligent Transporeation Systems,2002,3(1):37-47.
[27]Du Yu-feng,Schiller B,Krantz D.ALX:autonomous vehicle guidance for roadway following and abstacle avoidance.IEEE Intelligent Systems for the 21st Century,USA,1995:364-370.
[28]Koyasu H,Miura J,Shirai Y.Mobile robot navigation in dynamic environments using omnidirectional stereo.IEEE Robotics and Automation,USA,2003:893-898.
[29]Osama M,Nikolaos P P.A novel method for tracking and counting pedestrians in real-time using a single camera.IEEE Transactions on Vehicles Technology,2001,50(5):1267-1278.
[30]C.Wren A,Azarbayejfani T,Darrell et al.Real-time tracking of the human body.In Proceeding of the SPIE Conference on Integration Issues in area Commercial Media Delivery Systems,USA,1995:780-785.
[31]Haritaoglu 1,Harwood D,Davis L.W~4:A Real Time System for Detecting and Tracking People.Computer Vision and Pattern Recognition,USA,1998:962-962.
[32]Haritaoglu 1,Harwood D,Davis L.Hydra:Multiple people detection and tracking using silhouettes.Image Analysis and Processing,USA,1999:280-285.
[33]Zhao L,Thorpe C E.Stereo and neural network-based pedestrian detection.IEEE Tram on Intelligent Transportation Systems,2000,1(3):148-154.
[34]Viola P,Jones M J,Snow D.Detecting Pedestrian using patterns of motion and appearance.Computer Vision,2003,63(2):734-741.
[35]Masoud O,Papanikolo poulos N P.Robust pedestrian tracking using a model-based approach.Intelligent Transportation System,USA,1997:338-343.
[36]Wren C,Azarbayejani A,Darrell T et al.Pfinder.time tracking of the human body.IEEE Trans on Pattern Analysis and Machine Intelligence,1997,19(7):780-785.
[37]王亮,胡卫明,谭铁牛.人运动的视觉分析综述.计算机学报,2002,225(3):225-237.
[38]章疏晋.图像分割.北京:科学出版社,2001.
[39]邓聚龙。灰预测与会决策.武汉:华中科技大学出版社,2002.
[40]Sylvia Gil,Ruggero Milanese,Thierry Pun.Feature selection for object tracking in traffic scenes.SPIE,1994.
[41]Cecelja F,Balachandran W,Jirawimut R.A stereo vision system for pedestrian navigation.Applied Electromagnetics and Communications,USA,2003:30-33.
[42]郑江滨.视频监视方法研究:(博士学位论文).西安:西北工业大学,2002.
[43]B.Bascle,P.Bouthemy,R.Deriche et al.Tracking complex primitives in an image sequence.In 12th International Conference on Pattern Recognition,Jerusalem,Israel,1994:426-431.
[441 Baumberg,D.Hogg.An adaptive eigen-shape model.Proceedings of the 6th.British Vision Conference,USA,1995:87-96.
[45]V.Philomin,R.Duraiswami,L.Davis.Pedestrian tracking from a moving vehicle.Procs.IEEE Intelligent Vehicles Symposium,USA,2002:350-355.
[46]Kamijo K,Tanigawa T.Stock Price Pattern Recognition-A Recurrent Neural Network Approach.IEEE International Conference of Neural Networks,USA,1990:215-221.
[47]邵文坤,黄爱民,韦庆.目标跟踪方法综述.影像技术,2006,23(1):17-20.
[48]Kass M,Witkinm A,Terzopoulos D.Snakes.Active contour models.International Journal on Computer Vision,1998,1(4):321-331.
[49]Menet S,Saint-Marc P,Medioni G.B-snakes:Implementation and application to stereo.Proceedings of the DARPA Image Understanding Workshop,Pittsburgh,Pennsylvania,1990:720-726.
[50]Badenas J,Bober M.Motion and intensity-based segmentation and its application to traffic monitoring proceedings.International Conference on Image Analysis and Proceedings,Italy,1997:502-509.
[51]H.Moravec.Towards Automatic Visual Obstacle Avoidance.Proceedings of the 5th International Joint Conference on Artificial Intelligence,USA,1977:584-590.
[52]贾静平,赵荣椿.使用Mean Shift进行自适应序列图像目标跟踪.计算机应用研究,2005,22(2):247-249.
[53]朱胜利,朱善安,李旭超.快速运动目标的Mean shift跟踪算法.光电工程,2006,33(5):66-70.
[54]Comaniciu D,Ramesh V,Meer P.Real-Time tracking of non-rigid objects using mean shift.Proc.of the IEEE Conference on Computer Vision and Pattern Recognition,USA,2000:142-149.
[55]M.Bertozzi,A.Broggi,A.Fascioli et al.Pedestrian localization and tracking system with Kalman filtering.Procs.IEEE Intelligent Vehicles Symposium,Italy,2004:584-589.
[56]魏娟丽,翟社平,王万诚.视频序列中人体运动目标的检测与跟踪研究.计算机应用与软件,2006,23(4):139-141.
[57]汪颖进,张桂林.新的基于Kalman滤波的跟踪方法.红外与激光工程,2004,33(5):505-508.
[58]Ribaric S,Adrinek G,Segvic S.Real-time active visual tracking system.Electrotechnical Conference,USA,2004:231-234.
[59]张丽.车辆视频检测与跟踪系统的算法研究:(硕士学位论文).杭州:浙江大学,2003.
[2]王亮,胡卫明,谭铁牛.基于步态的身份识别.计算机学报,2006,26(3):353-360.
[3]Hong Cheng,Nanning Zheng,Junjie Qin.Pedestrian Detection Using Sparse Gabor Filter and Support Vector Machine.Intelligent Vehicles Symposium,USA,2005:583-587.
[4]田广,戚飞虎,朱文佳等。基于移动拍摄下基于人体部位的行人检测.系统仿真学报,2006,18(10):2906-2910.
[5]黄琛.基于Hausdorff距离模板匹配的行人检测算法研究与应用:(硕士学位论文).北京:清华大学,2006.
[6]M Bertozzi,A Broggi,R Chapuis et al.Shape-based Pedestrian Detection and Localization.Intelligent Vehicles Symposium 2003,USA,2003:410-415.
[7]B Heisele,C W ohler.Motion-based Recognition of Pedestrians.Intelligent Conference on Pattern Recognition,August,1998:1325-1330.
[8]Alan J,Lipton- Local Application of Optic flow to Analyze Rigid Versus NonOrigid Motion.Robotics Institute,USA,1999.
[9]V Philomin,R Duraiswami,L Davis.Pedestrian Tracking from a Moving Vehicle.Intelligent Vehicles Symposium,USA,2000:350-355.
[10]O Masoud.Robust Pedestrian Tracking Using a Model Obased Approach.Conference on Intelligent Transportation Systems,USA,1997:338-343.
[11]M Oren,C Papageorgiu,P Sihna et al.Pedestrian Detection using Wavelet Templates.Puerto Rico:Procs,IEConf.On Computer Vision and Pattern Recognition,June 1997:193-199.
[12]A Mohan,C Papageorgiou,T Poggio.Example-based Object Detection in Images by Components.IEEE Trausactiouson Pattern Analysis and Machine Intelligence,2001,23(4):349-361.
[13]A Broggi,A Fascioli,I Fedriga et al.Stereo-Based Preprocessing for Human Shape Localization in Unstructured Envimuments.IEEE Intelligent Vehicles Symposium2003,USA,2003:410-415.
[14]L Zhao,C Thorpe.Stereo and Neural Network-based Pedestrian Detection.IEEE Transaction son Intelligent Transportation Systems,2000,1(3):148-154.
[15]Neri A,Colonnese S,Rusao G et al.Automatic moving object and background separation.Signal Processing,1998,66(2):219-232.
[16]Kamijo S,Sakauchi M.Segmentation of vehicles and pedestrians in traffic scence by spatio-temporal Markov random field model.Multimedia and Expo,USA,2003:285-288.
[17]袁基炜,史忠科.一种图像序列自动分割新方法.计算机工程与应用,2004,29(3):144-148.
[18]Hiroshi Koyasu,Jun MIURA,Yoshiki Shirai.Realtime Omnidirectional Stereo for Obstacle Detection and Tracking in Dynamic Environments.IEEE Trans on Intelligent Transportation Systems,2001,5(6):244-251.
[19]Zhao L,Thorpe C E.Stereo and neural network-based pedestrian detection.IEEE Trans on Intelligent Transportation Systems,2000,1(3):148-154.
[20]STAUFFER C,GRIMSON W E L.Adaptive Background mixture models for real-time tracking.Proc.Conf.Computer Vision and Pattern Recognition,USA,1999:246-252.
[21]GIANLUCA B,MASSIMO B.Background estimation with Gaussian distribution for image segmentation,a fast approach.IEEE International Workshop on Measurement Systems for Homeland Security,Contraband Detection and Personal Safety Orlando,USA,2005:29-30.
[22]贺贵明,李凌娟,贾振堂.一种快速的基于对称差分的视频分割算法.小型微型计算机系统,2003,24(6):966-968.
[23]李刚,邱尚斌,林凌等.基于背景差法和帧间差法的运动目标检测方法.仪器仪表学报,2006。26(8):118-123.
[24]Chu J W,Ji L S,Guo L et al.Study on Method of Detecting Preceding Vehicle Based on Monocular Camera.IEEE Intelligent Vehicles,Pama,Italy,2004:750-755.
[25]Shin KATO,Kohji TOMITA,Sadayuki TSUGAWA.Visual Navigation along Reference Lines and Collision Avoidance for Autonomous Vehicles.IEEE Intelligent Vehicles Symposium,USA,1996:385-390.
[26]Surendra G,Osama M,Robert F et al.Detection and Classification of Vehicles.IEEE Transaction on Intelligent Transporeation Systems,2002,3(1):37-47.
[27]Du Yu-feng,Schiller B,Krantz D.ALX:autonomous vehicle guidance for roadway following and abstacle avoidance.IEEE Intelligent Systems for the 21st Century,USA,1995:364-370.
[28]Koyasu H,Miura J,Shirai Y.Mobile robot navigation in dynamic environments using omnidirectional stereo.IEEE Robotics and Automation,USA,2003:893-898.
[29]Osama M,Nikolaos P P.A novel method for tracking and counting pedestrians in real-time using a single camera.IEEE Transactions on Vehicles Technology,2001,50(5):1267-1278.
[30]C.Wren A,Azarbayejfani T,Darrell et al.Real-time tracking of the human body.In Proceeding of the SPIE Conference on Integration Issues in area Commercial Media Delivery Systems,USA,1995:780-785.
[31]Haritaoglu 1,Harwood D,Davis L.W~4:A Real Time System for Detecting and Tracking People.Computer Vision and Pattern Recognition,USA,1998:962-962.
[32]Haritaoglu 1,Harwood D,Davis L.Hydra:Multiple people detection and tracking using silhouettes.Image Analysis and Processing,USA,1999:280-285.
[33]Zhao L,Thorpe C E.Stereo and neural network-based pedestrian detection.IEEE Tram on Intelligent Transportation Systems,2000,1(3):148-154.
[34]Viola P,Jones M J,Snow D.Detecting Pedestrian using patterns of motion and appearance.Computer Vision,2003,63(2):734-741.
[35]Masoud O,Papanikolo poulos N P.Robust pedestrian tracking using a model-based approach.Intelligent Transportation System,USA,1997:338-343.
[36]Wren C,Azarbayejani A,Darrell T et al.Pfinder.time tracking of the human body.IEEE Trans on Pattern Analysis and Machine Intelligence,1997,19(7):780-785.
[37]王亮,胡卫明,谭铁牛.人运动的视觉分析综述.计算机学报,2002,225(3):225-237.
[38]章疏晋.图像分割.北京:科学出版社,2001.
[39]邓聚龙。灰预测与会决策.武汉:华中科技大学出版社,2002.
[40]Sylvia Gil,Ruggero Milanese,Thierry Pun.Feature selection for object tracking in traffic scenes.SPIE,1994.
[41]Cecelja F,Balachandran W,Jirawimut R.A stereo vision system for pedestrian navigation.Applied Electromagnetics and Communications,USA,2003:30-33.
[42]郑江滨.视频监视方法研究:(博士学位论文).西安:西北工业大学,2002.
[43]B.Bascle,P.Bouthemy,R.Deriche et al.Tracking complex primitives in an image sequence.In 12th International Conference on Pattern Recognition,Jerusalem,Israel,1994:426-431.
[441 Baumberg,D.Hogg.An adaptive eigen-shape model.Proceedings of the 6th.British Vision Conference,USA,1995:87-96.
[45]V.Philomin,R.Duraiswami,L.Davis.Pedestrian tracking from a moving vehicle.Procs.IEEE Intelligent Vehicles Symposium,USA,2002:350-355.
[46]Kamijo K,Tanigawa T.Stock Price Pattern Recognition-A Recurrent Neural Network Approach.IEEE International Conference of Neural Networks,USA,1990:215-221.
[47]邵文坤,黄爱民,韦庆.目标跟踪方法综述.影像技术,2006,23(1):17-20.
[48]Kass M,Witkinm A,Terzopoulos D.Snakes.Active contour models.International Journal on Computer Vision,1998,1(4):321-331.
[49]Menet S,Saint-Marc P,Medioni G.B-snakes:Implementation and application to stereo.Proceedings of the DARPA Image Understanding Workshop,Pittsburgh,Pennsylvania,1990:720-726.
[50]Badenas J,Bober M.Motion and intensity-based segmentation and its application to traffic monitoring proceedings.International Conference on Image Analysis and Proceedings,Italy,1997:502-509.
[51]H.Moravec.Towards Automatic Visual Obstacle Avoidance.Proceedings of the 5th International Joint Conference on Artificial Intelligence,USA,1977:584-590.
[52]贾静平,赵荣椿.使用Mean Shift进行自适应序列图像目标跟踪.计算机应用研究,2005,22(2):247-249.
[53]朱胜利,朱善安,李旭超.快速运动目标的Mean shift跟踪算法.光电工程,2006,33(5):66-70.
[54]Comaniciu D,Ramesh V,Meer P.Real-Time tracking of non-rigid objects using mean shift.Proc.of the IEEE Conference on Computer Vision and Pattern Recognition,USA,2000:142-149.
[55]M.Bertozzi,A.Broggi,A.Fascioli et al.Pedestrian localization and tracking system with Kalman filtering.Procs.IEEE Intelligent Vehicles Symposium,Italy,2004:584-589.
[56]魏娟丽,翟社平,王万诚.视频序列中人体运动目标的检测与跟踪研究.计算机应用与软件,2006,23(4):139-141.
[57]汪颖进,张桂林.新的基于Kalman滤波的跟踪方法.红外与激光工程,2004,33(5):505-508.
[58]Ribaric S,Adrinek G,Segvic S.Real-time active visual tracking system.Electrotechnical Conference,USA,2004:231-234.
[59]张丽.车辆视频检测与跟踪系统的算法研究:(硕士学位论文).杭州:浙江大学,2003.