全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于视频监控的运动目标跟踪算法

Keywords: 智能交通,视频监控,运动跟踪,特征匹配,Kalman滤波,灰色模型

Full-Text   Cite this paper   Add to My Lib

Abstract:

利用Kalman滤波思想对运动目标的前时刻状态信息进行预测,获取重心位置与形态紧密度估计值;将估计值与当前时刻观测值进行匹配,根据匹配误差修正运动目标的速度与紧密度变化值,通过递归算法实现常态下运动目标的准确、快速跟踪.针对复杂场景下由于运动遮挡造成无法准确估计目标运动轨迹,采用灰色模型GM(1,1)保证了跟踪过程的连续、稳定.最后,通过不同交通场景的视频序列对本文算法进行了验证,结果表明本文方法具有较好的适应性、鲁棒性,可实现复杂遮挡情况下连续、稳定、实时的目标运动跟踪.

References

[1]  KOLLER D,DANILIDIS K,NAGEL HH.Model-based object tracking in monocular image sequences of road traffic scenes[J].International Journal of Computer Vision,1993,10(3):257-281.
[2]  COIFMAN B,BEYMER D,MALIK J.A real-time computer vision system for vehicle tracking and traffic surveillance[J].Transport Res:Part C,1998,6(4):271-288.
[3]  PARAGIOS N,DERICHE R.Geodesic active regions:a new paradigm to deal with frame partition problems in computervision[J].Visual Commun Image Represent,2002:249-268.
[4]  KATO J,WATANABE T,JOGA S,et al.An HMM/MRF based stochastic framework for robust vehicle tracking[J].Intelligent Transportation Systems,2004,5(3):142-154.
[5]  RAD R,JAMZAD M.Real time classification and tracking of multiple vehicles in highways[J].Pattern Recognition Letters,2005,26:1597-1607.
[6]  林培群,徐建闽.复杂交通场景中运动车辆的检测与轨迹跟踪[J].华南理工大学学报:自然科学版,2008,36(6):84-89.LIN Pei-qun,XU Jian-min.Detection and trajectory tracking of moving vehicles in complicated traffic scene[J].Journal ofSouth China University of Technology:Natural Science Edition,2008,36(6):84-89.(in Chinese)
[7]  常好丽,史忠科.基于单目视觉的运动行人检测与跟踪方法[J].交通运输工程学报,2006,6(2):55-59.CHANG Hao-li,SHI Zhong-ke.Method of moving pedestrian detection and tracking based on monocular vision technology[J].Journal of Traffic and Transportation Engineering,2006,6(2):55-59.(in Chinese)
[8]  CUCCHIARA R,GRANAC,TARDINI G,et al.Probabilistic people tracking for occlusion handling[C]∥Proceedings of the17th International Conference on ICPR.Washington DC USA:IEEE Computer Society,2004,1:132-135.
[9]  ENG HL,WANG J X,KAM A H,et al.A bayesian framework for robust human detection and occlusion handling usinghuman shape model[C]∥Proceedings of the 17th International Conference on ICPR.Washing DC USA:IEEE ComputerSociety,2004,2:257-260.
[10]  李志慧,张长海,曲昭伟,等.交通流视频检测中背景初始化算法研究[J].吉林大学学报:工学版,2008,38(1):148-151.LI Zhi-hui,ZHANG Chang-hai,QU Zhao-wei,et al.Background initialization algorithm in traffic flow video detection[J].Journal of Jilin University:Engineering and Technology Edition,2008,38(1):148-151.(in Chinese)
[11]  杨淑莹.图像模式识别——VC++技术实现[M].北京:清华大学出版社,北京交通大学出版社,2005:143-145.
[12]  李志慧,张长海,曲昭伟,等.交通流视频检测中背景模型与阴影检测算法[J].吉林大学学报:工学版,2006,36(6):993-997.LI Zhi-hui,ZHANG Chang-hai,QU Zhao-wei,et al.Background extraction model and shadowdetection algorithm in trafficflow video detection[J].Journal of Jilin Universityl:Engineering and Technology Edition,2006,36(6):993-997.(inChinese)
[13]  郑南宁.计算机视觉与模式识别[M].北京:国防工业出版社,1998:131-133.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133