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...

一种自适应学习的混合高斯模型视频目标检测算法

DOI: 10.11834/jig.20100413

Keywords: 混合高斯模型,智能视频监控,自适应学习

Full-Text   Cite this paper   Add to My Lib

Abstract:

为解决背景模型的更新问题,提高视频运动目标检测性能,通过定义像素样本对模型更新的有效因子,提出一种自适应学习的混合高斯模型检测算法。用样本有效因子的历史累加量反映背景模型的质量,并用于动态调整模型更新速度。同时,对检测出的前景区域进行目标分析,由分析结果间接控制模型更新,保证更新的准确性和模型的稳定性。实验结果表明,该算法可以快速适应背景变化,同时保证目标检测的完整性。算法性能已在不同监控场景中得到验证。

References

[1]  Zoran Zivkovic,Recursive unsupervised learning of finite mixture models,IEEE Transactions on Pattern Analysis and Machine Intelligence,2004(5).
[2]  Thongkamwitoon T,Aramvith S,Chalidabhongse T H,An adaptive real-time background subtraction and moving shadows detection,New York:IEEE Press,2004.
[3]  Chris Stauffer,Eric W,Crimson L,Learning patterns of activityusing real-time tracking,IEEE Transactions on Pattern Analysis and Machine Intelligence,2000(8).
[4]  Kaewtrakulpong Pakorn,Bowden Richard,An improved adaptive background mixture model for real-time tracking with shadow detection,USA:kluwer Academic Publishers,2001.
[5]  Lee Dar-Shyang,Effective gaussian mixture learning,IEEE Transactions on Pattern Analysis and Machine Intelligence,2005(5).
[6]  Michael Harville,Gaile Gordon,John Woodfill,Foreground segmentation using adaptive mixture models in color and depth,New York:Computer Science Press,2001.
[7]  Chao Yuyan,Kenji Suzuki,A run-based two-scan labeling algorithm,IEEE Intelligent Transaction on Image Processing,2008(5).
[8]  Han Hongzhe.Wang Zhiling Adaptive background modeling with shadow suppression 2008

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133