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...

混合高斯模型和帧间差分相融合的自适应背景模型

DOI: 10.11834/jig.20080422

Keywords: 背景建模,混合高斯模型,运动目标检测,帧间差分

Full-Text   Cite this paper   Add to My Lib

Abstract:

提出了运动目标检测中背景动态建模的一种方法。该方法是在Stauffer等人提出的自适应混合高斯背景模型基础上,为每个像素构建混合高斯背景模型,通过融入帧间差分把每帧中的图像区分为背景区域、背景显露区域和运动物体区域。相对于背景区域,背景显露区中的像素点将以大的更新率更新背景模型,使得长时间停滞物体由背景变成运动前景时,被遮挡的背景显露区被快速恢复。与Stauffer等人提出的方法不同的是,物体运动区不再构建新的高斯分布加入到混合高斯分布模型中,减弱了慢速运动物体对背景的影响。实验结果表明,在有诸多不确定性因素的序列视频中构建的背景有较好的自适应性,能迅速响应实际场景的变化。

References

[1]  Wren C,Azarbayejani A,Darrell T,et al.Pfinder:real-time tracking of the human body[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):780~785.
[2]  Zivkovic Z.Improved adaptive Ganssian mixture model for back-ground subtraction[A].In:Proceedings of the 17th International Conference on Pattern Recognition[C],Cambridge,United Kingdom,2004,2:28~31.
[3]  Liu Ya,Ai Hai-zbou,Xu Guang-you.Moving object detection and tracking based on background subtraction[Ⅰ].Information and Con-trol,2002,31(4):315~319.[刘亚,艾海舟,徐光?.一种基于背景模型的运动目标检测与跟踪算法[J].信息与控制,2002,31(4):315~319.]
[4]  Ridder C,Munkeh O,Kirchner H.Adaptive background estimation and foreground detection using Kalman-fihering[A].In:Proceed-ings of the Int\'l Conference on Recent Advances Sinmechatronics[C],Istanbul,Turkey,1995:193~199.
[5]  Friedman N,Russell S.Image segmentation in video sequences:A probabilistic approach[A].In:Proceedings of the 13th Annual Conference on Uncertainty in Artificial Intelligence[C],Providence,Rhode Island,1997:175~181.
[6]  Stauffer C,Grimson W.Adaptive background mixture models for realo time tracking[A].In:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C],Fort Collins,Colorado,USA,1999:246~252.
[7]  Hayman E,Eklondh J.Statistical background subtraction for a mobile observer[A].In:Proceedings of the 9th International Conference on Computer Vision[C],Nice,France,2003:67~74.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133